© 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. 249025
    Prev
    Next
    INDEX
    Explanations

    alarm and crushing

    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
     нама
    0.63
     ሃ
    0.51
     पद्मा
    0.47
     ነገር
    0.47
     მათ
    0.46
     දු
    0.46
     அறிமுக
    0.45
     නිර්
    0.45
     ರೀತಿ
    0.45
     معاملہ
    0.45
    POSITIVE LOGITS
     implement
    0.53
     handel
    0.52
    p
    0.50
    ［
    0.50
    Ｐ
    0.50
     wars
    0.49
     vans
    0.45
     hava
    0.45
     repay
    0.44
     maakt
    0.44
    Activations Density 0.002%

    No Known Activations