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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64014
    Prev
    Next
    INDEX
    Explanations

    masculine names and place names

    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_34/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
    Retrouvez
    -1.27
    
    -1.17
    très
    -1.16
     indien
    -1.15
     Dinas
    -1.13
    Adverten
    -1.13
    notre
    -1.13
     welk
    -1.11
     Napoléon
    -1.10
    Ingrédients
    -1.09
    POSITIVE LOGITS
     Mike
    2.33
     Kevin
    2.31
     David
    2.30
     Michael
    2.28
     Richard
    2.27
     Andrew
    2.25
     Daniel
    2.22
     Mr
    2.17
     Robert
    2.16
     Steve
    2.14
    Activations Density 0.486%

    No Known Activations