© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105786
    Prev
    Next
    INDEX
    Explanations

    phrases and common co-occurrences

    np_acts-logits-general · gemini-2.5-flash-lite

    integration of models and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nię
    0.53
     অশ
    0.50
     కనిప
    0.49
     веке
    0.49
     Ψ
    0.49
     eigentlich
    0.48
     ابر
    0.48
     ψ
    0.46
     Бүгенге
    0.46
    铯
    0.46
    POSITIVE LOGITS
    at
    0.46
    h
    0.44
     roles
    0.43
     mere
    0.43
    सायन
    0.43
     Towa
    0.43
     segala
    0.42
    enburg
    0.41
    in
    0.41
     programa
    0.41
    Activations Density 0.001%

    No Known Activations