© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98803
    Prev
    Next
    INDEX
    Explanations

    identifies causes and their consequences

    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
    Negative Logits
    ]
    -3.06
    ization
    -2.56
    being
    -2.50
    [
    -2.48
    咂
    -2.38
    which
    -2.33
    because
    -2.27
    鲮
    -2.25
    see
    -2.25
    </i>
    -2.23
    POSITIVE LOGITS
    ↵↵
    2.88
     všech
    2.42
    ){
    2.30
     dětí
    2.30
     nový
    2.30
    </h4>
    2.28
    }
    2.23
    vignon
    2.20
    风的
    2.08
     cause
    2.06
    Activations Density 0.038%

    No Known Activations