© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49489
    Prev
    Next
    INDEX
    Explanations

    Q: questions and statements

    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
     alterações
    -0.89
     úteis
    -0.88
    жаться
    -0.84
    挽回
    -0.83
     keindahan
    -0.77
    verhältnis
    -0.76
     limpo
    -0.75
     flexível
    -0.74
    packung
    -0.73
    PERATURE
    -0.73
    POSITIVE LOGITS
    ologiques
    0.86
     terreno
    0.83
     say
    0.81
     Sede
    0.79
     ebenfalls
    0.78
     Filosof
    0.77
    hafen
    0.77
    влении
    0.74
     saying
    0.74
    IVIDUAL
    0.74
    Activations Density 0.018%

    No Known Activations