© 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. 117789
    Prev
    Next
    INDEX
    Explanations

    major international, extremely long

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

    captions, provided, logged, correct

    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
    ت
    0.61
    י
    0.55
    选择了
    0.53
    वे
    0.52
    i
    0.51
    ي
    0.51
     A
    0.49
     iMac
    0.49
     Calor
    0.48
    袈
    0.47
    POSITIVE LOGITS
     securing
    0.59
     legible
    0.54
     flattened
    0.50
     확보
    0.50
     verstehen
    0.49
     straightened
    0.48
    logback
    0.46
     straightening
    0.45
     realising
    0.45
     flattening
    0.45
    Activations Density 0.000%

    No Known Activations