© 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. 83341
    Prev
    Next
    INDEX
    Explanations

    weather events and internet

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

    strategists, business models

    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
    زيد
    0.55
    ل
    0.53
    לה
    0.49
    戲
    0.48
    វិធី
    0.45
    طار
    0.45
    نه
    0.44
    ל
    0.44
    麂
    0.44
    سي
    0.44
    POSITIVE LOGITS
     commonly
    0.48
    icum
    0.46
     atât
    0.46
     saw
    0.44
    大概
    0.43
     Samu
    0.43
    ведения
    0.43
     веду
    0.43
     Stage
    0.42
     fier
    0.42
    Activations Density 0.000%

    No Known Activations