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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5399
    Prev
    Next
    INDEX
    Explanations

    book titles and topics

    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_24_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
    웨어
    0.37
     supersede
    0.36
     НА
    0.36
     remastered
    0.35
    UTION
    0.34
     miscellaneous
    0.34
    ");
    0.33
    ્વાસ
    0.33
    "};
    0.33
     Плавание
    0.33
    POSITIVE LOGITS
    the
    0.38
    C
    0.37
     a
    0.35
     the
    0.34
    G
    0.32
    P
    0.32
    并
    0.31
    S
    0.31
     adlı
    0.31
     ，
    0.30
    Activations Density 0.005%

    No Known Activations