© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87234
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and special characters

    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_34/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
     })
    -0.82
    )!=
    -0.75
     خان
    -0.74
    
    -0.70
    astype
    -0.70
     участь
    -0.70
    mapStateToProps
    -0.69
     Бе
    -0.68
    Prze
    -0.67
     wasnt
    -0.67
    POSITIVE LOGITS
    kaitan
    0.82
    のではないでしょうか
    0.80
    Populate
    0.80
    觎
    0.79
    Gibson
    0.78
     phan
    0.77
    empi
    0.77
    director
    0.74
     Gibson
    0.74
     pertence
    0.73
    Activations Density 0.015%

    No Known Activations