© 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. 11191
    Prev
    Next
    INDEX
    Explanations

    to work

    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
     errMsg
    1.43
    BlogPost
    1.38
    manship
    1.32
    ୬
    1.31
     slew
    1.30
    伪
    1.26
    ˆ‚
    1.25
     सब्सिडी
    1.25
    푞
    1.25
     অন্তঃ
    1.24
    POSITIVE LOGITS
    ạt
    1.17
    মানা
    1.11
    此同时
    1.10
    ence
    1.07
    טית
    1.04
    おく
    1.01
     financieras
    1.00
     kehidupan
    1.00
    ता
    0.99
    ною
    0.99
    Activations Density 0.000%

    No Known Activations