© 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. 251699
    Prev
    Next
    INDEX
    Explanations

    tax-deductible donations

    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
     mortals
    0.50
     interrelated
    0.48
    IMUM
    0.46
     steadily
    0.45
     prone
    0.45
     mortar
    0.45
    Ⲕ
    0.45
    Dense
    0.45
    IGI
    0.44
     backpack
    0.43
    POSITIVE LOGITS
     filmp
    0.58
     Aix
    0.49
     FODC
    0.49
     Drexel
    0.48
     लगना
    0.47
    ूट
    0.46
    asks
    0.46
    organized
    0.45
    资
    0.45
     organisiert
    0.45
    Activations Density 0.000%

    No Known Activations