© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156187
    Prev
    Next
    INDEX
    Explanations

    sports trades or locations

    np_acts-logits-general · gemini-2.5-flash-lite

    ensure meter is used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dage
    0.48
    ",
    0.46
    »).
    0.45
    »,
    0.45
    ,
    0.44
    valve
    0.44
    ."
    0.44
    честве
    0.44
     pallet
    0.43
    >,
    0.43
    POSITIVE LOGITS
     அவை
    0.48
     Undergraduate
    0.48
     Guilherme
    0.48
     스마트
    0.48
     disputa
    0.46
     Basketball
    0.46
     GraphQL
    0.45
     মনোভাব
    0.45
    ektiv
    0.45
    提出的
    0.45
    Activations Density 0.001%

    No Known Activations