© 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. 57999
    Prev
    Next
    INDEX
    Explanations

    playstyle, points, plant, better

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

    focus, remember, still, happen, work, gentle

    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
    ী
    0.48
    ח
    0.47
     אך
    0.46
     меди
    0.46
     የተለያዩ
    0.44
     של
    0.44
     הי
    0.44
     הל
    0.44
     исключительно
    0.43
     명
    0.43
    POSITIVE LOGITS
    sax
    0.45
     favorables
    0.43
     birdies
    0.43
     sagt
    0.43
    ಾಗುತ್ತದೆ
    0.43
     kval
    0.43
     blir
    0.42
     financials
    0.42
     fiori
    0.41
     momenta
    0.41
    Activations Density 0.000%

    No Known Activations