© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84413
    Prev
    Next
    INDEX
    Explanations

    variable identifiers and operators

    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
     of
    -1.73
     mereka
    -1.53
     их
    -1.32
     but
    -1.30
     them
    -1.26
    ]);
    -1.24
    #%%
    
    -1.23
     miatt
    -1.22
     който
    -1.20
    月から
    -1.20
    POSITIVE LOGITS
     nutzt
    1.53
    一些
    1.43
     poursuivre
    1.33
     zeichnet
    1.32
     versteht
    1.27
     was
    1.27
     with
    1.27
     ändert
    1.27
     empfiehlt
    1.27
    扩大
    1.25
    Activations Density 0.073%

    No Known Activations