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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67872
    Prev
    Next
    INDEX
    Explanations

    axisaxis, axes

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

    The neuron detects numeric literal tokens (integer constants) in code or technical 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
    Արտաքին
    -1.16
    vertido
    -1.13
     avenir
    -1.09
     without
    -1.08
     even
    -1.08
     only
    -1.06
     with
    -1.05
     that
    -1.05
     almost
    -1.05
     Sekund
    -1.05
    POSITIVE LOGITS
    ENCIL
    1.12
     hemi
    1.04
    ETHOD
    1.03
    itares
    1.03
     kraju
    0.98
    kheim
    0.96
    atique
    0.95
     ряд
    0.93
     throng
    0.93
    bosity
    0.93
    Activations Density 0.001%

    No Known Activations