© 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. 123938
    Prev
    Next
    INDEX
    Explanations

    contributed to development

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

    const followed by type

    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
     Lookout
    0.47
     Windy
    0.47
     beziehen
    0.46
     Rights
    0.45
    meer
    0.43
     Carolyn
    0.42
     იქ
    0.42
     Verge
    0.42
     Rejected
    0.42
    إ
    0.42
    POSITIVE LOGITS
    ам
    0.56
    олові
    0.56
    쮿
    0.49
    ன்
    0.49
     увагу
    0.48
    чне
    0.47
    elliptic
    0.47
     către
    0.46
    зд
    0.46
     equation
    0.46
    Activations Density 0.000%

    No Known Activations