© 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. 34127
    Prev
    Next
    INDEX
    Explanations

    The post production

    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
    NewRow
    -1.16
     adverten
    -1.10
     externa
    -1.09
    dacia
    -1.02
    でしたか
    -1.02
     essencial
    -1.01
     ilustracja
    -1.00
    órica
    -1.00
     робити
    -1.00
    warnai
    -1.00
    POSITIVE LOGITS
    '
    1.25
    grenze
    1.13
    .
    1.05
    ap
    1.03
    甚至
    1.02
     aquesta
    1.02
     dessa
    1.00
    lets
    0.99
    ana
    0.99
    ms
    0.98
    Activations Density 0.001%

    No Known Activations