© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    inquiry words

    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
    ”
    -1.91
    A
    -1.87
    –
    -1.83
     самой
    -1.82
     sudadera
    -1.77
     appelée
    -1.75
     vergleich
    -1.73
     actuellement
    -1.71
     parfois
    -1.66
    よりも
    -1.66
    POSITIVE LOGITS
    𝒃
    1.80
     hiv
    1.77
    Gön
    1.74
     carolina
    1.67
     because
    1.63
    hadiran
    1.55
     thefe
    1.53
    ším
    1.47
    Cultura
    1.46
    افر
    1.45
    Activations Density 0.013%

    No Known Activations