© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10730
    Prev
    Next
    INDEX
    Explanations

    htmlspecialchars, dfs, encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ﺮ
    2.43
    ﻪ
    2.32
    ﺪ
    2.23
    AndKeys
    2.21
    ﻊ
    2.09
    sects
    2.06
     अलावा
    2.03
     UND
    2.01
    foresaid
    2.01
    न्होंने
    1.99
    POSITIVE LOGITS
    an
    2.61
    ي
    2.59
    m
    2.57
    мер
    2.46
    ры
    2.45
    ا
    2.44
    i
    2.35
    مول
    2.30
    tı
    2.30
    িয়ান
    2.30
    Activations Density 0.030%

    No Known Activations