© 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-65K
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    word prefixes and their completions

    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_65k_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
    e
    0.90
    s
    0.68
    a
    0.67
     under
    0.61
    eight
    0.58
    ️
    0.57
    een
    0.56
    ی
    0.54
    ea
    0.53
    는
    0.52
    POSITIVE LOGITS
    rying
    0.84
    restrial
    0.82
    <unused1219>
    0.77
    ଣ
    0.77
    ଖ
    0.75
    дов
    0.73
    incipal
    0.71
    rible
    0.69
    ств
    0.69
    кий
    0.69
    Activations Density 0.329%

    No Known Activations