© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123624
    Prev
    Next
    INDEX
    Explanations

    end of year

    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_10/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
     to
    -1.97
     or
    -1.65
     sumamente
    -1.56
    One
    -1.53
     â
    -1.48
     require
    -1.45
     and
    -1.41
    geſ
    -1.40
    Three
    -1.37
     extremadamente
    -1.34
    POSITIVE LOGITS
    ︕
    1.52
     ragaz
    1.48
     chofe
    1.45
     fubject
    1.39
     istan
    1.39
     comportements
    1.34
     jezt
    1.32
    
    1.31
     cuit
    1.31
     vaqueros
    1.31
    Activations Density 0.032%

    No Known Activations