© 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. 119041
    Prev
    Next
    INDEX
    Explanations

    discussion and comments

    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
    announced
    -0.85
    ʽ
    -0.82
     extrapolation
    -0.81
    Requests
    -0.79
     Kredit
    -0.74
     предприятия
    -0.72
    vestimento
    -0.72
     prezenta
    -0.71
    handleSubmit
    -0.71
    Interpolation
    -0.70
    POSITIVE LOGITS
     notes
    2.11
     comments
    1.74
     comment
    1.73
     Notes
    1.54
     note
    1.43
    comment
    1.41
    notes
    1.41
    Notes
    1.37
     Comment
    1.37
    Comment
    1.34
    Activations Density 0.034%

    No Known Activations