© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6832
    Prev
    Next
    INDEX
    Explanations

    color definitions and UI elements

    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_31_width_16k_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
     থেকে
    0.54
    Cleanup
    0.53
     intel
    0.52
     näher
    0.52
    NotFoundError
    0.52
     ->
    0.50
    Fail
    0.50
    NotNull
    0.50
    嘛
    0.50
    讠
    0.50
    POSITIVE LOGITS
    घाडी
    0.59
    தேச
    0.54
    タリア
    0.52
    heds
    0.52
    )|$(
    0.52
     EdgeInsets
    0.51
     BorderRadius
    0.50
     Innovations
    0.50
     innovations
    0.50
     attacked
    0.49
    Activations Density 0.051%

    No Known Activations