© 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. 198526
    Prev
    Next
    INDEX
    Explanations

    doing, obtained, save, index, chapter, engineer

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

    software coupling and design

    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
    桕
    0.51
    ність
    0.47
     něj
    0.45
    筅
    0.44
    璺
    0.43
    ньо
    0.43
    住房
    0.43
    apsingToolbar
    0.42
     войск
    0.42
    痍
    0.42
    POSITIVE LOGITS
    ja
    0.52
     melodies
    0.48
    cognitive
    0.46
     douloureuse
    0.46
     monomers
    0.46
    </strong>
    0.45
    strategies
    0.44
     disorders
    0.44
     percolation
    0.44
     epidemics
    0.44
    Activations Density 0.000%

    No Known Activations