© 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. 67234
    Prev
    Next
    INDEX
    Explanations

    version numbers and updates

    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
     lecker
    -1.13
    Antibodies
    -1.12
     cuivre
    -1.10
     великолеп
    -1.10
    หรือ
    -1.08
     vermel
    -1.07
    넋
    -1.06
     neón
    -1.05
    幔
    -1.05
     аромат
    -1.05
    POSITIVE LOGITS
     always
    1.56
     includes
    1.23
     update
    1.21
     user
    1.20
     also
    1.20
     updates
    1.19
     including
    1.17
     updated
    1.09
     проблеми
    1.09
     such
    1.08
    Activations Density 0.015%

    No Known Activations