© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39399
    Prev
    Next
    INDEX
    Explanations

    displaying, selling, blocking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ことが多い
    -0.95
    ïc
    -0.91
    Wre
    -0.86
     cuadrado
    -0.83
    Gom
    -0.82
    átní
    -0.82
     Estructura
    -0.81
    expectedResult
    -0.80
     cuyo
    -0.79
     Manajemen
    -0.79
    POSITIVE LOGITS
     its
    1.72
    where
    1.19
    Its
    1.13
     interno
    1.09
     such
    1.00
    ⒉
    0.99
    vgili
    0.99
    食べられる
    0.98
    тинг
    0.96
    करण
    0.96
    Activations Density 0.100%

    No Known Activations