© 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. 58107
    Prev
    Next
    INDEX
    Explanations

    predicting common word continuations

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

    phrases starting with or containing specified words

    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
     haber
    0.51
     mezcla
    0.48
    buje
    0.46
    ﻬ
    0.45
     tipo
    0.45
     nuova
    0.44
    вые
    0.43
     roce
    0.43
    вая
    0.42
     febbraio
    0.42
    POSITIVE LOGITS
     Auswirkungen
    0.53
     schönsten
    0.52
     سنج
    0.49
     Bata
    0.47
     TouchUtils
    0.47
     Chirurgien
    0.47
     opérés
    0.46
     крупней
    0.46
    𝕕
    0.46
    ချုပ်
    0.45
    Activations Density 0.000%

    No Known Activations