© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    mixtures

    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
     harp
    0.69
     resetButton
    0.64
     Frühstück
    0.62
     DSL
    0.61
    莊
    0.60
     чтобы
    0.58
     Wins
    0.58
    ISTIC
    0.58
    `${
    0.58
     Â
    0.58
    POSITIVE LOGITS
     mathvariant
    0.97
    getTransforms
    0.77
    akaran
    0.76
    essentially
    0.75
    Fight
    0.74
     disampaikan
    0.73
    פו
    0.73
    }></
    0.72
    physics
    0.72
    ൻ
    0.71
    Activations Density 0.001%

    No Known Activations