© 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. 35912
    Prev
    Next
    INDEX
    Explanations

    API

    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
     Essas
    0.78
    ônica
    0.77
    暁
    0.77
     großer
    0.76
    ához
    0.75
     pazienti
    0.75
    antiago
    0.74
    ának
    0.73
     financieras
    0.72
    ínsula
    0.72
    POSITIVE LOGITS
    k
    1.14
    c
    1.09
    h
    1.02
    m
    0.97
    the
    0.91
    t
    0.91
    e
    0.91
    tons
    0.90
    w
    0.89
    cations
    0.85
    Activations Density 0.067%

    No Known Activations