© 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. 4485
    Prev
    Next
    INDEX
    Explanations

    characters and names

    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
    ным
    1.22
    ουν
    1.15
    skom
    1.02
    ığımız
    1.01
    นิด
    1.00
    น้อย
    0.97
    ologique
    0.97
    珹
    0.96
    㝒
    0.95
    有一個
    0.94
    POSITIVE LOGITS
    ри
    1.26
    га
    1.05
    с
    1.02
    б
    1.00
     а
    0.98
     Мі
    0.98
    an
    0.93
    ви
    0.91
     Ре
    0.90
    s
    0.90
    Activations Density 0.063%

    No Known Activations