© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    Python dunder methods

    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
    osław
    2.62
    내는
    2.51
    akang
    2.41
    ic
    2.36
     »
    2.35
    uet
    2.33
    ிறது
    2.28
    ubarb
    2.28
    انب
    2.27
    ərbay
    2.25
    POSITIVE LOGITS
    𝙩
    3.55
    tp
    3.36
    𝙡
    3.25
    𝙤
    3.04
    𝙧
    2.90
    <bos>
    2.88
    𝙖
    2.88
    ेटिव
    2.72
    흉
    2.71
    Cro
    2.67
    Activations Density 0.043%

    No Known Activations