© 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. 249632
    Prev
    Next
    INDEX
    Explanations

    product instructions or warnings

    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
     جوړونکو
    0.49
     treball
    0.46
     মাঝি
    0.46
    襬
    0.45
    竇
    0.45
     kucch
    0.44
     vị
    0.43
    かく
    0.41
     পরিচাল
    0.41
     працю
    0.41
    POSITIVE LOGITS
    收获
    0.51
    0.50
     Illumina
    0.48
    hints
    0.47
     $
    0.45
     Illumin
    0.45
     Lightroom
    0.45
    ew
    0.44
     GoPro
    0.44
    endif
    0.44
    Activations Density 0.001%

    No Known Activations