© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31803
    Prev
    Next
    INDEX
    Explanations

    current time, interface, following

    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
     Roux
    0.74
     Routine
    0.74
    を起こ
    0.73
     neum
    0.73
    烊
    0.72
     soles
    0.72
    VAE
    0.72
     Ares
    0.72
     AirPods
    0.71
     Tyre
    0.71
    POSITIVE LOGITS
    ).”
    0.73
     philanthropist
    0.72
     researcher
    0.71
     philanth
    0.71
    :”
    0.71
     brooks
    0.71
    )”
    0.70
    )”.
    0.69
    으나
    0.68
    \},
    0.68
    Activations Density 0.000%

    No Known Activations