© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10634
    Prev
    Next
    INDEX
    Explanations

    catch up

    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
     conjunta
    1.93
    芏
    1.90
     américain
    1.88
    тные
    1.82
     capaces
    1.77
     potência
    1.76
     ouvertes
    1.73
     padrões
    1.73
     промышлен
    1.72
     francês
    1.72
    POSITIVE LOGITS
     glimpse
    1.75
    ah
    1.69
    al
    1.62
     glimpses
    1.52
    с
    1.52
    bearer
    1.50
    <0x8C>
    1.34
     {
    1.34
    ship
    1.31
    che
    1.30
    Activations Density 0.009%

    No Known Activations