© 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. 11242
    Prev
    Next
    INDEX
    Explanations

    explaining why or providing specifics

    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
    ه
    1.22
    or
    1.12
    ا
    1.10
    가
    1.09
    ה
    1.07
     ((
    1.05
     {(
    1.00
    ो
    0.99
     (
    0.99
    er
    0.96
    POSITIVE LOGITS
     vocals
    1.29
    譎
    1.25
     refreshments
    1.23
    umbnail
    1.22
     matchup
    1.22
    欷
    1.22
    janje
    1.21
     timestamp
    1.20
    valmentaja
    1.19
     thumbnailUrl
    1.19
    Activations Density 0.588%

    No Known Activations