© 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. 11638
    Prev
    Next
    INDEX
    Explanations

    có thể

    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
    independent
    2.23
    abling
    2.09
    डे
    2.09
    ᡳ
    2.06
    آم
    2.02
    𝙙
    1.99
    ewnątrz
    1.96
    ことを
    1.96
    iak
    1.95
    conversion
    1.93
    POSITIVE LOGITS
     Pre
    2.45
    sth
    2.41
    髓
    2.40
    亥
    2.31
    posites
    2.31
    десят
    2.28
    ussy
    2.28
    skraft
    2.27
    pstmt
    2.24
     pkg
    2.24
    Activations Density 0.000%

    No Known Activations