© 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. 22-GEMMASCOPE-RES-131K
    7. 73218
    Prev
    Next
    INDEX
    Explanations

    quality descriptors and comparisons

    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_22/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
    Therapie
    -1.13
     Профиль
    -1.07
     staunch
    -1.07
     tedavi
    -1.05
     corrientes
    -1.02
     seguras
    -1.02
     perspectivas
    -1.02
    unidade
    -1.00
     cualidades
    -0.99
     capacidades
    -0.98
    POSITIVE LOGITS
     and
    2.02
     because
    1.63
     than
    1.32
     compared
    1.27
     but
    1.16
     since
    1.16
     poiché
    1.11
    *),
    1.10
     THAN
    1.07
    และ
    1.05
    Activations Density 0.084%

    No Known Activations