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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130189
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis and quotes

    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
    KILL
    -0.95
     normalmente
    -0.89
     walaupun
    -0.89
    FRI
    -0.88
    AUF
    -0.87
    向了
    -0.87
    casus
    -0.86
    TRAP
    -0.84
    originally
    -0.83
    BOTH
    -0.82
    POSITIVE LOGITS
     then
    1.09
     proposed
    1.03
     it
    0.98
    inverno
    0.98
     decided
    0.94
    Präsident
    0.89
     decide
    0.86
     offered
    0.85
     hạt
    0.85
    ოლი
    0.85
    Activations Density 0.007%

    No Known Activations