© 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. 71264
    Prev
    Next
    INDEX
    Explanations

    finish with

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

    finishing things

    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
     for
    0.79
    t
    0.75
     has
    0.71
    ted
    0.66
     an
    0.66
    the
    0.66
     premises
    0.65
     by
    0.64
     fallacy
    0.63
     xhrObj
    0.62
    POSITIVE LOGITS
    ро
    0.92
    리
    0.89
    ку
    0.85
    ول
    0.77
    éri
    0.76
    ية
    0.75
    ون
    0.75
    টা
    0.75
    ור
    0.75
    it
    0.74
    Activations Density 0.038%

    No Known Activations