© 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. 45264
    Prev
    Next
    INDEX
    Explanations

    Unqualified, feelings, nba, Vuitton

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.76
     dianteira
    -1.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.61
    </h6>
    -1.61
    Ᏹ
    -1.59
    ↵↵↵↵↵↵↵↵↵↵
    -1.58
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.57
    
    
    -1.56
    POSITIVE LOGITS
     in
    2.64
     of
    1.98
     other
    1.63
     the
    1.60
     on
    1.59
     some
    1.56
     andere
    1.55
     or
    1.55
     atau
    1.41
     et
    1.40
    Activations Density 0.001%

    No Known Activations