© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8997
    Prev
    Next
    INDEX
    Explanations

    options and categories

    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
    RecordPtr
    0.55
     tb
    0.54
    疮
    0.51
    億
    0.51
     mouvement
    0.50
     feminist
    0.49
     கண்கா
    0.48
     шей
    0.48
     debugging
    0.47
    쩡
    0.47
    POSITIVE LOGITS
    Choices
    1.07
     choices
    1.03
    dropdown
    1.03
     options
    1.02
    options
    1.02
    choices
    1.02
     Enum
    1.01
    enum
    1.00
    Enum
    1.00
     Options
    1.00
    Activations Density 0.357%

    No Known Activations