© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59244
    Prev
    Next
    INDEX
    Explanations

    code and formatting

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

    This neuron is specialized to pick up numeric tokens—sequences of digits (e.g. line numbers, version numbers, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    webView
    -0.90
    denver
    -0.84
    PageRoute
    -0.76
     webView
    -0.76
     tirantes
    -0.75
     )}$
    -0.75
    няли
    -0.75
     McCain
    -0.75
     Brücken
    -0.75
     fãs
    -0.74
    POSITIVE LOGITS
    <h2>
    1.07
    ]{
    0.94
     Comentarios
    0.90
    ATE
    0.78
     Jacek
    0.77
    </tr>
    0.77
    }{\
    0.77
    LEGAL
    0.76
    FRAME
    0.75
    immel
    0.75
    Activations Density 0.000%

    No Known Activations