© 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. 12085
    Prev
    Next
    INDEX
    Explanations

    Vicuna or Walter Gropius

    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
    ia
    3.99
    м
    3.77
    ル
    3.57
    𝖽
    3.29
    ва
    3.15
    𝗅
    3.07
    ী
    3.06
    특별시
    2.85
    𝗇
    2.85
    ം
    2.79
    POSITIVE LOGITS
    ted
    4.00
    ך
    3.82
    ০০
    3.77
    க்
    3.46
    ech
    3.44
    ties
    3.38
    ton
    3.38
    𝘷
    3.32
    yya
    3.27
    ために
    3.23
    Activations Density 0.092%

    No Known Activations