© 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. 109703
    Prev
    Next
    INDEX
    Explanations

    questions and creative descriptions

    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
    ₂,
    -0.84
     however
    -0.82
     multiple
    -0.82
    죄
    -0.81
    emptyList
    -0.79
     trainings
    -0.77
    合わせた
    -0.77
    lustre
    -0.76
     alike
    -0.76
    trac
    -0.75
    POSITIVE LOGITS
    凄く
    1.00
     véhic
    0.94
     sicherlich
    0.93
     doskon
    0.93
    vencia
    0.92
    konfirmasi
    0.91
     еще
    0.88
    色々と
    0.87
     débat
    0.86
    ritter
    0.85
    Activations Density 0.002%

    No Known Activations