© 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. 34-GEMMASCOPE-RES-131K
    7. 23743
    Prev
    Next
    INDEX
    Explanations

    are permitted provided

    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_34/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
    zav
    -0.75
    ್ಯ
    -0.71
    ASSO
    -0.70
     Ausrüstung
    -0.68
    rades
    -0.68
     Eso
    -0.68
    iora
    -0.67
     tarjeta
    -0.67
    тябрь
    -0.67
     Staffing
    -0.66
    POSITIVE LOGITS
     Universität
    0.69
    拡大
    0.66
     Regina
    0.66
     され
    0.65
     nya
    0.65
    дневно
    0.63
    Karla
    0.63
     variegated
    0.63
     Winkler
    0.62
    куда
    0.61
    Activations Density 0.050%

    No Known Activations