© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246788
    Prev
    Next
    INDEX
    Explanations

    verdict

    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
    Negative Logits
    শ
    0.47
     KeyEvent
    0.45
     Clancy
    0.45
    adığı
    0.45
    ၉
    0.45
    盛
    0.45
    йд
    0.44
    옹
    0.44
    ９
    0.44
    apiKey
    0.44
    POSITIVE LOGITS
    Verdict
    0.51
     دروس
    0.47
     bero
    0.47
     verdicts
    0.46
     mainframe
    0.45
     overalls
    0.44
     value
    0.44
     indoctr
    0.43
     aerospace
    0.43
    foils
    0.42
    Activations Density 0.000%

    No Known Activations