© 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. 236442
    Prev
    Next
    INDEX
    Explanations

    Please useapproximate prices

    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
    拍攝
    0.50
     [<
    0.48
    播出
    0.47
     chairperson
    0.46
    狹
    0.46
    拍摄
    0.45
    ,<
    0.44
    workspace
    0.44
    じん
    0.44
    ,{\
    0.43
    POSITIVE LOGITS
     begg
    0.49
    R
    0.49
    ry
    0.47
    U
    0.47
    N
    0.46
     gorg
    0.45
    bukti
    0.45
     SB
    0.45
    ai
    0.44
    punkt
    0.44
    Activations Density 0.000%

    No Known Activations