© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77371
    Prev
    Next
    INDEX
    Explanations

    news and questions

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

    The neuron fires on terminology around online software/service availability and access—words like “online,” “multiplayer,” “download,” “app store,” 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_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
    ны
    -0.89
     valeur
    -0.87
     даже
    -0.87
     waschen
    -0.86
    ؐ
    -0.86
    ⍳
    -0.85
    opheles
    -0.84
    〜
    -0.84
    これを
    -0.84
    ;//
    -0.84
    POSITIVE LOGITS
    スポンサーリンク
    1.02
    <?
    0.98
    ¿½
    0.97
     legate
    0.94
    startX
    0.93
    IVERSITY
    0.93
     http
    0.93
    枓
    0.91
     vieta
    0.91
    ГЛА
    0.90
    Activations Density 0.009%

    No Known Activations