© 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. 103430
    Prev
    Next
    INDEX
    Explanations

    forming collections or collaborations

    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
    ↵↵
    -1.93
    ↵
    -1.83
    K
    -1.77
    }
    -1.74
     use
    -1.64
    6
    -1.59
     et
    -1.58
    ;
    -1.55
    ка
    -1.55
    </td>
    -1.53
    POSITIVE LOGITS
    arschu
    2.03
    
    1.80
     them
    1.70
    гії
    1.70
     volonté
    1.62
    然後
    1.60
    跸
    1.60
    哢
    1.58
    ösen
    1.54
    並且
    1.54
    Activations Density 0.008%

    No Known Activations