© 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. 22-GEMMASCOPE-2-RES-262K
    7. 4477
    Prev
    Next
    INDEX
    Explanations

    level: defining categories or types

    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_22_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
     suara
    0.83
     আওয়
    0.81
    ྭ
    0.81
    깬
    0.78
    ጋገብ
    0.78
     mån
    0.77
    ﺛ
    0.77
    よび
    0.77
    গ
    0.77
    ברת
    0.76
    POSITIVE LOGITS
     Remember
    1.10
     If
    1.09
     Hopefully
    1.09
    If
    1.08
    if
    1.04
    Remember
    1.04
     remember
    1.01
    Hopefully
    1.01
     Ultimately
    1.00
     Note
    0.99
    Activations Density 0.001%

    No Known Activations