© 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. 235119
    Prev
    Next
    INDEX
    Explanations

    intellect, aroma, rights

    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
     ٣
    0.47
     মার্চের
    0.45
    ５
    0.45
    স্
    0.44
    aughters
    0.43
     будів
    0.43
    児童
    0.43
    ။
    0.43
     Comptes
    0.42
    ׳
    0.41
    POSITIVE LOGITS
     odor
    0.56
     الزام
    0.50
     intellect
    0.49
     insur
    0.46
     aroma
    0.45
     गणना
    0.45
     intelekt
    0.45
     odors
    0.43
     numbness
    0.43
     अधिकारों
    0.42
    Activations Density 0.001%

    No Known Activations