© 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. 40199
    Prev
    Next
    INDEX
    Explanations

    нужны, верен, жны, жен, рав, жна

    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
     of
    -2.58
    ":
    -2.02
    姈
    -1.91
    ा
    -1.82
    Ꮨ
    -1.78
    nologia
    -1.77
    Ehrungen
    -1.75
    a
    -1.72
    ሖ
    -1.67
     jedną
    -1.66
    POSITIVE LOGITS
    UREAU
    2.02
    \
    1.87
    s
    1.81
     edificios
    1.73
     are
    1.73
    heureux
    1.72
    -“
    1.70
    猡
    1.58
     trinken
    1.55
    łecz
    1.54
    Activations Density 0.010%

    No Known Activations