© 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. 38917
    Prev
    Next
    INDEX
    Explanations

    position and size

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

    The neuron never activates—it doesn’t detect any particular pattern in the text.

    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
    /}{
    -1.36
     vė
    -1.23
     in
    -1.20
     mengalir
    -1.20
    卨
    -1.13
    そして
    -1.08
    齟
    -1.06
    もあった
    -1.06
    7
    -1.05
     naudoti
    -1.04
    POSITIVE LOGITS
     northwest
    1.16
     southwest
    1.09
     emphas
    1.06
    ところです
    1.05
     Она
    1.05
     northwestern
    1.02
    BindingResult
    1.02
    judic
    1.01
     Recently
    1.00
    来看
    1.00
    Activations Density 0.002%

    No Known Activations