© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 921
    Prev
    Next
    INDEX
    Explanations

    form

    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
    я
    1.38
    ות
    1.18
     formulated
    1.17
     onclick
    1.10
     contrary
    1.09
    vý
    1.09
    Боль
    1.05
     fuori
    1.04
    ेंजर
    1.04
    <0x89>
    1.02
    POSITIVE LOGITS
    idable
    2.45
    ूले
    1.86
    ative
    1.82
    ulates
    1.80
    ulate
    1.79
    ulated
    1.75
    ulating
    1.70
    ulations
    1.65
    atter
    1.63
     geométricas
    1.58
    Activations Density 0.164%

    No Known Activations