© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14547
    Prev
    Next
    INDEX
    Explanations

    scientific notation or measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric values, particularly those that appear in scientific or technical contexts, such as measurements or mathematical expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron does not consistently activate on any recurring textual pattern—it appears effectively inactive and finds no distinctive feature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cended
    -0.98
     høj
    -0.95
     bilder
    -0.93
    зик
    -0.88
    tismo
    -0.87
     Fotografie
    -0.86
    Wahl
    -0.85
     endnu
    -0.85
     ещё
    -0.85
    ppled
    -0.84
    POSITIVE LOGITS
     fairytale
    1.13
     rheinland
    1.04
     BorderSide
    1.04
     pestaña
    1.01
     Wohnzimmer
    1.01
     dotyczy
    0.99
     оригі
    0.98
     pretože
    0.97
     Gdy
    0.96
     cómodo
    0.95
    Activations Density 0.000%

    No Known Activations