© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10379
    Prev
    Next
    INDEX
    Explanations

    emoji, Resize, monster transitions

    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
    Negative Logits
    𝚎
    3.01
    ުރ
    2.63
    𝚒
    2.56
    ゚
    2.53
    ärte
    2.49
    𝙞
    2.49
    iert
    2.42
    insta
    2.36
    يها
    2.36
    é
    2.35
    POSITIVE LOGITS
     tratti
    2.77
    \
    2.73
     aspire
    2.72
     neckline
    2.70
    <tbody>
    2.59
    $)$.
    2.53
    ோ
    2.47
     တော့
    2.39
    ревно
    2.33
    TTLE
    2.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.