© 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. 247992
    Prev
    Next
    INDEX
    Explanations

    :

    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
    코
    0.47
     Italien
    0.46
    보
    0.46
    وت
    0.45
     tubercles
    0.44
    마
    0.44
    樂
    0.44
    大
    0.44
    天文
    0.42
    او
    0.42
    POSITIVE LOGITS
     دی۔
    0.49
     czynności
    0.49
    Interrupt
    0.48
    стный
    0.48
     aplicación
    0.46
     இப்ப
    0.45
     乾燥
    0.45
     รถ
    0.44
    Failure
    0.44
    inescent
    0.43
    Activations Density 0.001%

    No Known Activations