© 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. 35107
    Prev
    Next
    INDEX
    Explanations

    App, DB, Runtime, Pride, Identity

    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
    ر
    1.26
     Isometric
    1.16
    ко
    1.13
     Ejec
    1.07
    ो
    1.05
    р
    1.05
     র
    1.02
     ര
    1.02
     изготов
    1.02
     Chủ
    1.02
    POSITIVE LOGITS
     monolayers
    1.09
     Moe
    0.92
    Space
    0.91
     surrounding
    0.90
    tas
    0.90
    AIN
    0.89
    alta
    0.88
    ats
    0.86
    jima
    0.86
    ERN
    0.85
    Activations Density 0.001%

    No Known Activations