© 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. 2887
    Prev
    Next
    INDEX
    Explanations

    # followed by identifiers or numbers

    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
    𝐭
    3.04
    southeast
    2.80
    lichen
    2.76
    ्यों
    2.72
    pere
    2.65
    ᵏ
    2.58
    Browse
    2.53
    Harvey
    2.53
    cience
    2.50
    licher
    2.50
    POSITIVE LOGITS
    <bos>
    3.20
    ed
    2.95
    edik
    2.77
    Repost
    2.73
    rrggbb
    2.59
     bos
    2.58
     উল্লেখ
    2.42
     mL
    2.42
    æk
    2.41
    鸯
    2.41
    Activations Density 0.021%

    No Known Activations