© 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. 41930
    Prev
    Next
    INDEX
    Explanations

    TR, traditions, toy

    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
    н
    1.27
    к
    1.26
    ма
    1.08
    й
    1.05
    нк
    0.98
    ৫
    0.95
    ху
    0.94
    ти
    0.93
    𝗺
    0.93
    𝘇
    0.93
    POSITIVE LOGITS
    IST
    0.99
     connue
    0.96
    OS
    0.93
    )}}
    0.93
    HS
    0.89
     devenue
    0.88
    aito
    0.87
    యితే
    0.87
     <!--<
    0.86
    IO
    0.86
    Activations Density 0.000%

    No Known Activations