© 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. 87586
    Prev
    Next
    INDEX
    Explanations

    surface area

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

    bot commands and arguments

    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
    ﻞ
    0.59
    setRoi
    0.57
    setUrl
    0.51
     Viceroy
    0.51
    pengaruhi
    0.50
    itipi
    0.49
     Raipur
    0.49
    राजा
    0.49
     можем
    0.49
     друже
    0.48
    POSITIVE LOGITS
     components
    0.46
     [
    0.46
     awarding
    0.44
     außer
    0.44
     bal
    0.44
    除了
    0.41
    wendung
    0.41
    ป
    0.41
     horaires
    0.40
     besides
    0.40
    Activations Density 0.000%

    No Known Activations