© 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. 164299
    Prev
    Next
    INDEX
    Explanations

    track record

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

    describing specific items or concepts

    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
     vrouw
    0.64
     तिजारत
    0.59
     ľud
    0.55
    टावा
    0.55
     gustaría
    0.54
    ))_{
    0.54
     vrouwen
    0.54
    Ⲗ
    0.54
     mujer
    0.53
     জীবের
    0.53
    POSITIVE LOGITS
    t
    0.59
    in
    0.51
     will
    0.48
    %
    0.47
    nich
    0.46
    d
    0.46
     no
    0.46
    ens
    0.45
     Son
    0.45
    end
    0.44
    Activations Density 0.001%

    No Known Activations