© 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. 167922
    Prev
    Next
    INDEX
    Explanations

    specific conditions and details

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

    encountered something

    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
    时
    0.48
    ầu
    0.46
    ường
    0.46
    emain
    0.46
    ập
    0.45
    Sah
    0.44
    ן
    0.44
     equipado
    0.43
    ę
    0.43
    ھے
    0.43
    POSITIVE LOGITS
    festival
    0.47
    ⸩
    0.46
    ॉर्क
    0.44
    porque
    0.43
    fak
    0.43
    blusas
    0.43
     andro
    0.42
     patitth
    0.42
     recounted
    0.42
     Gewalt
    0.41
    Activations Density 0.001%

    No Known Activations