© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21252
    Prev
    Next
    INDEX
    Explanations

    SC- followed by numbers or codes

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

    The neuron fires on any standalone “sc” or “SC” token (often in environment or macro names like SC_…, SC-…, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    There
    -2.64
    It
    -2.59
     Each
    -2.55
     Surprisingly
    -2.48
    Surprisingly
    -2.47
     Depending
    -2.36
    Although
    -2.34
     Therefore
    -2.33
     Occasionally
    -2.33
    ,
    -2.28
    POSITIVE LOGITS
    0
    3.28
    "
    2.25
    an
    2.25
    罽
    2.23
    h
    2.19
    鞮
    2.13
     avec
    2.09
     recognises
    1.99
     his
    1.96
     enorme
    1.95
    Activations Density 0.016%

    No Known Activations