© 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. 11091
    Prev
    Next
    INDEX
    Explanations

    president of

    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
     puerta
    0.82
    ูนย์
    0.82
    кинуло
    0.77
    쌉
    0.75
    IN
    0.75
     modernisation
    0.72
    ინ
    0.71
     magically
    0.71
    ？」
    0.70
    െയി
    0.70
    POSITIVE LOGITS
    it
    1.20
    ic
    1.10
    ')
    1.06
    le
    1.02
    ians
    0.98
    ong
    0.98
    uk
    0.97
    es
    0.96
    k
    0.93
    al
    0.93
    Activations Density 0.000%

    No Known Activations