© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 32043
    Prev
    Next
    INDEX
    Explanations

    bind, fun, subscriptions, mitochondria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ए
    1.66
    1.48
     а
    1.46
    gown
    1.41
    К
    1.41
     हे
    1.39
    𝑰
    1.39
    II
    1.36
    ляю
    1.36
    І
    1.34
    POSITIVE LOGITS
    ski
    1.96
    y
    1.95
    u
    1.91
    ود
    1.88
    ians
    1.86
     priors
    1.83
    s
    1.80
    m
    1.70
    sch
    1.68
    س
    1.63
    Activations Density 0.000%

    No Known Activations