© 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. 34-GEMMASCOPE-RES-131K
    4. 109889
    Prev
    Next
    INDEX
    Explanations

    mathematical and code constructs

    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_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
     daire
    -0.94
     daba
    -0.94
     recha
    -0.92
     ebenfalls
    -0.91
    ୈ
    -0.90
     også
    -0.90
     departamentos
    -0.89
    icked
    -0.88
     figuras
    -0.88
    Hvis
    -0.88
    POSITIVE LOGITS
    </em>
    1.05
     xxl
    0.87
     :>
    0.84
     Hl
    0.84
     dieselbe
    0.82
    むしろ
    0.82
     lte
    0.82
     Tl
    0.80
     Grizzlies
    0.79
     pistes
    0.78
    Activations Density 0.034%

    No Known Activations