© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11848
    Prev
    Next
    INDEX
    Explanations

    home appliances and electronics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    то
    3.66
    ुणा
    3.59
    д
    3.51
    ৮
    3.27
    gehend
    3.19
    に
    3.17
    та
    2.95
    로
    2.78
    νά
    2.78
    de
    2.70
    POSITIVE LOGITS
    ه
    4.92
    o
    3.64
    ে
    3.13
    ો
    2.76
    e
    2.75
    oque
    2.71
    oC
    2.70
    います
    2.64
    chaften
    2.58
    ம்
    2.56
    Activations Density 0.007%

    No Known Activations