© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12235
    Prev
    Next
    INDEX
    Explanations

    import from

    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
     from
    -1.52
     with
    -1.31
     there
    -1.23
     will
    -1.20
     through
    -1.15
     only
    -1.02
     perawatan
    -1.01
     emphasizing
    -1.00
     would
    -0.98
     other
    -0.98
    POSITIVE LOGITS
     mettre
    1.03
     envoyer
    1.00
    がなく
    1.00
     ſtate
    0.98
    がありません
    0.97
     coordon
    0.96
     créer
    0.96
     Raiders
    0.96
     Kosten
    0.91
     fournir
    0.91
    Activations Density 0.008%

    No Known Activations