© 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. 10-GEMMASCOPE-RES-131K
    7. 44655
    Prev
    Next
    INDEX
    Explanations

    closing comment block```

    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
     This
    -2.55
    これを
    -2.11
     If
    -2.06
     Makes
    -1.95
     There
    -1.73
     Having
    -1.71
     '':
    -1.70
     When
    -1.70
     While
    -1.69
     ALWAYS
    -1.69
    POSITIVE LOGITS
    
    1.95
    踽
    1.88
    fortunately
    1.86
    possibly
    1.86
     Conſ
    1.84
    鲧
    1.80
    婠
    1.80
    probably
    1.79
    渽
    1.79
     白い
    1.78
    Activations Density 0.026%

    No Known Activations