© 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. 221026
    Prev
    Next
    INDEX
    Explanations

    stylish top, Resources section

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

    project viability, revisions, exploration

    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
     ress
    0.52
    畏
    0.48
    izantes
    0.47
    ان
    0.46
     gestures
    0.45
     passages
    0.44
    غرافيا
    0.44
    威胁
    0.42
    ته
    0.42
    انيه
    0.42
    POSITIVE LOGITS
     Sudanese
    0.50
     Controvers
    0.50
     Sudan
    0.46
     kepercayaan
    0.46
     রেকর্ড
    0.45
    ked
    0.45
    )$-
    0.44
     cải
    0.44
     Javed
    0.43
     Ekonom
    0.43
    Activations Density 0.000%

    No Known Activations