© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    struggling with thoughts

    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
    ن
    2.05
    it
    1.95
    ras
    1.83
    ა
    1.83
    ang
    1.81
    č
    1.81
    м
    1.77
    ना
    1.73
    chten
    1.71
    rische
    1.71
    POSITIVE LOGITS
    ый
    1.98
    顿
    1.68
    ῴ
    1.57
     Irma
    1.54
    bardziej
    1.51
    DidChange
    1.48
    涹
    1.48
    Ꮮ
    1.44
    ग्रस्त
    1.43
     特許庁
    1.42
    Activations Density 0.070%

    No Known Activations