© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    Gestures

    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
    ر
    2.72
    еру
    2.52
    िंग
    2.46
    s
    2.32
    িয়ে
    2.26
    다는
    2.25
    nya
    2.21
    er
    2.20
    د
    2.18
    sels
    2.16
    POSITIVE LOGITS
    inheritDoc
    2.68
    裟
    2.59
    foresaid
    2.50
     setDescription
    2.42
    urney
    2.39
    ủ
    2.34
    ணா
    2.32
    ζα
    2.31
    ัญหา
    2.29
    ̉a
    2.27
    Activations Density 0.000%

    No Known Activations