© 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-65K
    7. 4479
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings or transitions

    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_65k_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
     pesticides
    2.14
     mustn
    2.04
    愀
    2.01
     insecticide
    1.99
     insecticides
    1.98
     pesticide
    1.97
     conseille
    1.97
     plantings
    1.95
     Dorey
    1.94
    漀
    1.93
    POSITIVE LOGITS
    end
    0.98
    1
    0.82
    int
    0.78
    en
    0.73
    let
    0.72
    inde
    0.70
    top
    0.69
    rest
    0.69
    all
    0.69
    un
    0.68
    Activations Density 0.231%

    No Known Activations