© 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. 198794
    Prev
    Next
    INDEX
    Explanations

    detecting errors or difficulties

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

    language and specific concepts

    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
     primeiras
    0.44
     primeras
    0.43
    T
    0.40
    werke
    0.38
    首次
    0.37
     त्यासाठी
    0.37
    for
    0.35
    mathbf
    0.35
    ㈠
    0.35
    에서의
    0.34
    POSITIVE LOGITS
     மட்டுமல்ல
    0.55
     शिलालेख
    0.49
     emojis
    0.47
     occasionally
    0.46
     নানান
    0.45
     undisclosed
    0.44
     undetected
    0.43
     parfois
    0.43
     oublier
    0.43
     encrypted
    0.43
    Activations Density 0.001%

    No Known Activations