© 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. 147887
    Prev
    Next
    INDEX
    Explanations

    scope, condition, and availability

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

    explaining why something works

    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
    л
    0.48
    نتی
    0.44
    נות
    0.43
    ნ
    0.42
    nelle
    0.42
    CCOCC
    0.41
    ン
    0.40
    犠
    0.40
     مكت
    0.39
     indire
    0.39
    POSITIVE LOGITS
     പ്രസി
    0.44
    পরিচিত
    0.43
     praz
    0.42
     rhizosphere
    0.42
     nazy
    0.42
     ditu
    0.42
     prazo
    0.41
     själv
    0.41
    ழுகு
    0.41
     bellissimo
    0.40
    Activations Density 0.001%

    No Known Activations