© 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. 34-GEMMASCOPE-RES-131K
    7. 64173
    Prev
    Next
    INDEX
    Explanations

    license clauses and disclaimers

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

    The neuron fires on boilerplate header or license blocks (e.g. copyright/license notice, separator lines, file-or-email header metadata).

    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
     europé
    -0.82
     Cook
    -0.82
     Gestaltung
    -0.74
     токси
    -0.73
    期限
    -0.73
     Ward
    -0.72
     ditemukan
    -0.71
     probably
    -0.71
     News
    -0.70
    angi
    -0.70
    POSITIVE LOGITS
     כד
    0.91
    挿入
    0.85
    Somehow
    0.84
     Kowal
    0.77
     ^
    0.76
    enregistrement
    0.75
     Throwing
    0.74
    갸
    0.74
    캬
    0.74
    doctype
    0.74
    Activations Density 0.002%

    No Known Activations