© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13258
    Prev
    Next
    INDEX
    Explanations

    groups, file format, toxicological, familial pronouns

    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
     koper
    -1.23
    urige
    -1.20
     моих
    -1.12
     жесто
    -1.10
     mario
    -1.08
     COLD
    -1.06
    municipio
    -1.05
    ,
    -1.05
     vilka
    -1.05
     известных
    -1.05
    POSITIVE LOGITS
     our
    2.34
     we
    1.78
     skvě
    1.71
     Bakterien
    1.63
     unserer
    1.63
     שלנו
    1.57
     nuestro
    1.56
     nosso
    1.54
    浤
    1.52
     nuestra
    1.52
    Activations Density 0.028%

    No Known Activations