© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102917
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    窠
    -1.91
     für
    -1.78
     like
    -1.77
    ."
    -1.75
    }$,
    -1.74
     striving
    -1.73
     heightened
    -1.72
     suoi
    -1.69
    靭
    -1.68
    ”,
    -1.67
    POSITIVE LOGITS
    糴
    1.79
    鲥
    1.77
     zoude
    1.77
     開封
    1.76
     花纹
    1.76
     ビキニ
    1.73
     westfalen
    1.71
     enten
    1.70
     Obr
    1.68
    
    1.67
    Activations Density 0.010%

    No Known Activations