© 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. 187613
    Prev
    Next
    INDEX
    Explanations

    detecting transmitting signals

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

    introduces definition

    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
    an
    0.55
    man
    0.54
    h
    0.53
    reihe
    0.49
    li
    0.48
    viel
    0.48
     Dunn
    0.46
    durch
    0.45
     Draper
    0.45
     Bianchi
    0.45
    POSITIVE LOGITS
     aumenta
    0.54
     ফেব্র
    0.51
    입
    0.50
     julio
    0.50
    টাল
    0.49
     extremadamente
    0.49
     cometido
    0.48
     esperamos
    0.48
     aumentó
    0.48
    বা
    0.47
    Activations Density 0.001%

    No Known Activations