© 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. 67243
    Prev
    Next
    INDEX
    Explanations

    Daniel Radcliffe

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

    The neuron primarily activates on numeric literals in source code (digits and related punctuation).

    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
     or
    -2.52
    -
    -1.48
     which
    -1.38
    ,
    -1.38
     jezelf
    -1.31
     Looks
    -1.30
    </strong>
    -1.29
     resultaat
    -1.28
    --
    -1.27
     volledig
    -1.27
    POSITIVE LOGITS
     their
    1.83
     aussit
    1.80
     his
    1.64
     perguntou
    1.57
     espanhol
    1.55
     bäst
    1.55
    鰊
    1.55
    webtoken
    1.53
     tasche
    1.52
     сфере
    1.52
    Activations Density 0.004%

    No Known Activations