© 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. 33429
    Prev
    Next
    INDEX
    Explanations

    software, numbers, questions

    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
     interesante
    -1.24
     pedras
    -1.16
    gans
    -1.13
    nější
    -1.11
     gancho
    -1.10
    DidChange
    -1.09
     století
    -1.08
     витами
    -1.06
     seyn
    -1.04
    adone
    -1.03
    POSITIVE LOGITS
    ⅽ
    1.27
    TokenNameDOT
    1.19
     maaf
    1.05
     motiva
    1.04
     utk
    1.02
     blauwe
    1.02
     kleuren
    1.02
     покрытие
    1.01
     will
    0.99
     tekno
    0.99
    Activations Density 0.014%

    No Known Activations