© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118763
    Prev
    Next
    INDEX
    Explanations

    C# dispose method

    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
     nice
    -0.73
     rentrer
    -0.70
     ক
    -0.70
    いえ
    -0.69
     Cayenne
    -0.68
     смогли
    -0.67
    opts
    -0.66
     بچه
    -0.66
     лиш
    -0.65
    licka
    -0.65
    POSITIVE LOGITS
    гре
    0.72
     smartphones
    0.69
     ré
    0.68
     españoles
    0.67
     aspecto
    0.66
    стого
    0.66
    тропо
    0.65
     desaparecido
    0.65
    弔
    0.64
    iQ
    0.64
    Activations Density 0.036%

    No Known Activations