© 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. 11603
    Prev
    Next
    INDEX
    Explanations

    look like, 【text】

    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
    ᵖ
    2.65
    shot
    2.64
    轅
    2.47
    ोजन
    2.40
    டித்த
    2.40
    WORTH
    2.26
    鹂
    2.25
    ുടെ
    2.23
    Elater
    2.22
     ধরেই
    2.22
    POSITIVE LOGITS
    ak
    2.85
    c
    2.66
    િક્
    2.63
    poison
    2.63
    y
    2.62
    cı
    2.59
    akte
    2.55
    u
    2.47
    ম
    2.45
    Cre
    2.45
    Activations Density 0.006%

    No Known Activations