© 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. 10641
    Prev
    Next
    INDEX
    Explanations

    or followed by comparison

    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
    an
    1.07
    u
    1.01
    adays
    1.00
    其中的
    0.95
    >\<^
    0.89
    on
    0.88
    ாது
    0.86
    act
    0.82
     fonctionnal
    0.82
    estimator
    0.82
    POSITIVE LOGITS
    ﺪ
    0.96
    ssss
    0.94
    ς
    0.92
    瘩
    0.90
    ﺬ
    0.90
     Aí
    0.87
    Ко
    0.87
    РО
    0.86
    ראל
    0.86
    ভাই
    0.85
    Activations Density 0.040%

    No Known Activations