© 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. 205166
    Prev
    Next
    INDEX
    Explanations

    company brands services

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

    KB, MB, GB, TB

    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
    Појединачна
    0.52
     decomp
    0.51
    謢
    0.50
     envisaged
    0.49
     সম্মুখীন
    0.48
     মির
    0.48
     luxuries
    0.48
    inescence
    0.47
    Unhandled
    0.46
     psyched
    0.46
    POSITIVE LOGITS
    abo
    0.47
    aba
    0.45
    חי
    0.44
    की
    0.43
     FEST
    0.43
    ड
    0.43
    बार
    0.42
    חת
    0.42
    इ
    0.42
    му
    0.42
    Activations Density 0.000%

    No Known Activations