© 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. 12052
    Prev
    Next
    INDEX
    Explanations

    photo followed by metadata or content

    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
    д
    3.98
    م
    3.90
    ן
    3.49
    ума
    3.38
    ল
    3.19
    س
    3.15
    tól
    3.07
    ഗി
    3.05
    tand
    2.99
    ηση
    2.96
    POSITIVE LOGITS
    ة
    3.81
    ed
    3.56
    ﺭ
    3.15
     höchste
    3.00
    a
    2.94
    o
    2.92
    ा
    2.91
     zakres
    2.85
    es
    2.83
    aal
    2.70
    Activations Density 0.022%

    No Known Activations