© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    author tag followed by name

    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
    由于
    -1.09
     abonnement
    -1.07
     biografi
    -0.99
     大きい
    -0.98
     respecte
    -0.98
     leurs
    -0.98
     Gratis
    -0.97
     TAMBÉM
    -0.97
     stadion
    -0.97
    still
    -0.97
    POSITIVE LOGITS
     public
    1.49
    public
    1.41
     what
    1.30
     get
    1.29
     void
    1.19
     such
    1.09
     gets
    1.02
     olduğunu
    0.95
     will
    0.95
     What
    0.95
    Activations Density 0.001%

    No Known Activations