© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2965
    Prev
    Next
    INDEX
    Explanations

    kit

    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
    s
    1.15
    ς
    1.01
    ات
    0.90
    sessions
    0.87
    ‌است
    0.87
    serrat
    0.83
     egli
    0.82
     dihasil
    0.81
    가를
    0.79
     aptly
    0.77
    POSITIVE LOGITS
    ına
    1.17
    ان
    1.16
    rary
    1.00
    न
    1.00
    ong
    0.99
    agem
    0.97
    ica
    0.96
    aría
    0.96
    icket
    0.95
     halinde
    0.93
    Activations Density 0.001%

    No Known Activations