© 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. 10-GEMMASCOPE-RES-131K
    7. 72574
    Prev
    Next
    INDEX
    Explanations

    foreign words or technical 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_10/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
     to
    -1.91
     or
    -1.85
     as
    -1.73
     but
    -1.34
    -
    -1.31
     vairāk
    -1.30
     in
    -1.29
    oughed
    -1.27
     except
    -1.27
     now
    -1.23
    POSITIVE LOGITS
    Also
    1.38
     nawet
    1.38
     尺寸
    1.35
     enamorado
    1.35
    場所に
    1.32
     récord
    1.32
    Without
    1.32
     corredores
    1.29
    Using
    1.27
     wykonania
    1.27
    Activations Density 0.144%

    No Known Activations