© 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. 35109
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    t
    1.38
    د
    1.38
    ال
    1.29
    ます
    1.27
    ت
    1.22
    Targets
    1.08
    PIT
    1.07
    ง
    1.05
    Се
    1.05
    Console
    1.02
    POSITIVE LOGITS
    it
    1.46
    ва
    1.41
    ার
    1.31
    ções
    1.24
    াধিকার
    1.20
    itie
    1.18
    ান
    1.17
     Однако
    1.16
     tende
    1.16
    ージュ
    1.16
    Activations Density 0.002%

    No Known Activations