© 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. 96658
    Prev
    Next
    INDEX
    Explanations

    multi-lingual conceptual associations

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

    just knowing or voicing

    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
    i
    0.56
    ic
    0.52
    getPrototypeOf
    0.49
    #
    0.46
    ['-
    0.45
     outcrop
    0.45
     المره
    0.45
    a
    0.45
    N
    0.45
    mar
    0.44
    POSITIVE LOGITS
     smatra
    0.50
     koment
    0.48
     bestaat
    0.46
     Gesù
    0.46
    平静
    0.46
     pidió
    0.46
    昛
    0.44
    ས་
    0.44
     солдат
    0.44
     besteht
    0.44
    Activations Density 0.001%

    No Known Activations