© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12640
    Prev
    Next
    INDEX
    Explanations

    struct declarations

    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
    pite
    2.44
    ました
    2.33
    ﮄ
    2.28
    ning
    2.28
    uju
    2.27
    nen
    2.23
    rita
    2.23
    ˆ
    2.23
    }^{*}$,
    2.23
    之内
    2.18
    POSITIVE LOGITS
    s
    2.51
    inset
    2.42
    ോ
    2.29
    onion
    2.28
    場合に
    2.27
    Kp
    2.20
    йга
    2.18
    ᒪ
    2.17
    갸
    2.17
    AppDesigner
    2.16
    Activations Density 0.000%

    No Known Activations