© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    google.com domains

    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
    ulado
    2.93
    ulty
    2.69
    alam
    2.68
    ӟ
    2.66
    ローブ
    2.63
    枻
    2.59
    ₴
    2.59
    preconnect
    2.58
    ⦖
    2.57
    ែម
    2.56
    POSITIVE LOGITS
    ুদ্ধ
    2.26
    er
    2.16
    e
    2.13
    leşt
    2.11
    ெ
    2.09
    THING
    2.08
    ment
    2.07
    ெழு
    2.07
    ักษณ์
    2.06
    ক্লো
    2.02
    Activations Density 0.019%

    No Known Activations