© 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. 103886
    Prev
    Next
    INDEX
    Explanations

    design your De visual hair meetings following of you izing

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

    lack or inability

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ŝ
    0.48
     Poem
    0.46
     sugars
    0.45
     aguas
    0.45
     Po
    0.45
     Categor
    0.45
     sanitary
    0.44
     ion
    0.42
     Poetry
    0.42
     within
    0.42
    POSITIVE LOGITS
    ﹏
    0.49
     недоста
    0.48
     عارف
    0.46
    на
    0.44
     어려
    0.44
     unavailability
    0.43
    fundamentals
    0.43
    ärte
    0.43
     inadequacy
    0.43
    ‏:‏
    0.43
    Activations Density 0.001%

    No Known Activations