© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13681
    Prev
    Next
    INDEX
    Explanations

    direction

    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_16k_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
    ח
    1.62
    ży
    1.49
    дя
    1.48
    োষ
    1.40
    ەر
    1.36
    ੇ
    1.33
    ারা
    1.32
    א
    1.32
    чать
    1.30
    Í
    1.29
    POSITIVE LOGITS
    முகச்
    1.67
     richting
    1.66
     direção
    1.64
    Direction
    1.59
     방향
    1.50
     कॉनक
    1.41
    নির্
    1.40
     kren
    1.39
    ிறது
    1.38
    SuppressWarnings
    1.38
    Activations Density 0.157%

    No Known Activations