© 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. 38881
    Prev
    Next
    INDEX
    Explanations

    new, perfect, chasing, advertising

    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
     Appet
    0.76
     truy
    0.75
     u
    0.73
     Послед
    0.71
     Review
    0.70
     Far
    0.69
     t
    0.68
    complement
    0.68
     kunt
    0.67
     After
    0.67
    POSITIVE LOGITS
    ො
    0.84
    onitrile
    0.75
    ड
    0.70
    യുടെ
    0.69
     кни
    0.69
    ebvre
    0.68
    ки
    0.68
    会被
    0.68
    osate
    0.68
     manifests
    0.68
    Activations Density 0.000%

    No Known Activations