© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58182
    Prev
    Next
    INDEX
    Explanations

    restaurants and places

    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
     JAMES
    -1.02
     куро
    -1.01
     Almighty
    -0.93
     épreuves
    -0.93
     ROBERT
    -0.92
     límites
    -0.91
     Bought
    -0.88
     koste
    -0.88
    Brands
    -0.88
    istert
    -0.86
    POSITIVE LOGITS
     typical
    1.01
     Two
    0.89
     by
    0.89
     reasonably
    0.89
     two
    0.88
     declines
    0.88
     μὲν
    0.87
     typically
    0.86
     at
    0.86
     time
    0.84
    Activations Density 0.013%

    No Known Activations