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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7938
    Prev
    Next
    INDEX
    Explanations

    dota2 TI, Attack on Titan, Freddie Gibbs

    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
    ﺎ
    1.08
     இருப்பினும்
    1.06
    ל
    1.00
    ক
    1.00
     тобто
    0.97
    ს
    0.97
     dvs
    0.95
    ಗೆ
    0.94
     बेहतरीन
    0.94
    場合の
    0.94
    POSITIVE LOGITS
    ,
    1.43
    ，
    1.16
    ‍या
    1.05
    ide
    1.04
    앗
    1.03
    ?
    1.02
    ers
    1.00
     Goog
    0.98
     Repo
    0.97
     (
    0.96
    Activations Density 0.180%

    No Known Activations