© 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. 14010
    Prev
    Next
    INDEX
    Explanations

    quantities and percentages

    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
     and
    -2.14
     also
    -1.62
     также
    -1.59
    yh
    -1.51
    also
    -1.46
     także
    -1.46
     
    -1.44
     επίσης
    -1.41
    brigens
    -1.40
    lý
    -1.39
    POSITIVE LOGITS
     where
    1.96
     that
    1.62
     this
    1.59
     it
    1.51
     the
    1.46
     their
    1.45
     these
    1.44
     dragón
    1.44
    nitř
    1.44
     said
    1.41
    Activations Density 0.088%

    No Known Activations