© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1778
    Prev
    Next
    INDEX
    Explanations

    file path elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Hawks
    1.52
    ReadAll
    1.41
     #
    1.39
    ToUpper
    1.38
    IsNullOr
    1.37
     DMA
    1.35
     emerged
    1.35
     #[
    1.34
    #,
    1.33
    rational
    1.33
    POSITIVE LOGITS
     föld
    0.79
     マット
    0.76
     cins
    0.76
    GINIA
    0.75
    rogens
    0.73
     Installing
    0.72
     Clk
    0.71
     cerdo
    0.71
    ފައި
    0.70
     veroor
    0.70
    Activations Density 0.128%

    No Known Activations