© 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. 22-GEMMASCOPE-RES-131K
    7. 128201
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects numeric literal tokens (especially floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    program code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Ưu
    -0.94
     will
    -0.90
     combining
    -0.89
    剥
    -0.87
    <td>
    -0.85
    т
    -0.84
     group
    -0.84
    )++;
    -0.83
    付
    -0.83
    يت
    -0.82
    POSITIVE LOGITS
    棵
    1.07
    $-$
    0.98
    setta
    0.94
    擼
    0.94
    トゥー
    0.94
     PROFESSIONAL
    0.91
    😊
    0.91
    medy
    0.91
     plafon
    0.91
     teint
    0.90
    Activations Density 0.015%

    No Known Activations