© 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. 232399
    Prev
    Next
    INDEX
    Explanations

    company involvement

    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
    źdz
    0.51
     درمیان
    0.47
    ಾದರೆ
    0.47
    ijj
    0.47
    ikke
    0.47
    isinde
    0.46
    خ
    0.45
     رع
    0.45
    atte
    0.45
    nå
    0.45
    POSITIVE LOGITS
     linguistics
    0.49
     Linguistics
    0.44
    演奏
    0.43
     SEEK
    0.43
     institute
    0.43
    ﻂ
    0.42
     enjoy
    0.42
     seek
    0.42
    Seek
    0.42
     enjoying
    0.41
    Activations Density 0.000%

    No Known Activations