© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 4887
    Prev
    Next
    INDEX
    Explanations

    boxed mathematical answers

    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
     temps
    0.88
     პროფილი
    0.86
    timevals
    0.86
    irie
    0.84
     পাকিস্তানীদের
    0.84
    <unused95>
    0.83
     funciones
    0.82
    (_,
    0.82
     rootCmd
    0.81
    ྒ
    0.81
    POSITIVE LOGITS
     fra
    0.70
     accum
    0.63
    εκ
    0.62
    比較
    0.62
     Fra
    0.61
    නේ
    0.60
     Transportation
    0.59
    eb
    0.59
     involuntarily
    0.58
    fra
    0.58
    Activations Density 0.001%

    No Known Activations