© 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. 44008
    Prev
    Next
    INDEX
    Explanations

    places and proper nouns

    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
    Donativos
    -2.42
    
    -2.36
     –
    -2.36
    鲵
    -2.31
    蹓
    -2.30
    踅
    -2.17
    *
    -2.16
     erhielten
    -2.13
     nahmen
    -2.11
     mussten
    -2.09
    POSITIVE LOGITS
    .
    3.45
     }
    2.25
    ￬
    2.16
    琑
    2.13
    },
    1.98
     proven
    1.97
    ⚥
    1.95
     quando
    1.95
    </em>
    1.85
    龉
    1.84
    Activations Density 0.003%

    No Known Activations