© 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. 84507
    Prev
    Next
    INDEX
    Explanations

    California, protein, London, Republic

    np_acts-logits-general · gemini-2.5-flash-lite

    capitalized words or acronyms, especially names and titles in all-caps.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     your
    -1.88
     on
    -1.76
     our
    -1.68
     we
    -1.36
     you
    -1.34
     felicità
    -1.30
     there
    -1.28
     protože
    -1.28
    photographe
    -1.20
     Problemen
    -1.17
    POSITIVE LOGITS
     estekak
    1.50
     travaillent
    1.47
     mereka
    1.41
    //});
    1.38
     brilli
    1.33
     They
    1.32
    !");
    1.30
     تلویزیون
    1.30
    IVER
    1.30
    !");
    
    1.30
    Activations Density 0.782%

    No Known Activations