© 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. 11099
    Prev
    Next
    INDEX
    Explanations

    conduct thorough inspections

    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
    勰
    2.71
    եռ
    2.59
    PathResource
    2.43
    ◸
    2.42
    फारिश
    2.38
    ounds
    2.33
    INVISIBLE
    2.31
    idc
    2.31
    ैंड
    2.31
    ंध
    2.28
    POSITIVE LOGITS
    <bos>
    2.29
    house
    2.25
    য়া
    2.24
     כן
    2.03
    urbance
    2.03
    ழுகு
    2.01
    otions
    1.97
    leti
    1.92
     EVER
    1.90
    hous
    1.87
    Activations Density 0.057%

    No Known Activations