© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48187
    Prev
    Next
    INDEX
    Explanations

    pagan, heathen, Gentile

    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
    });
    -2.33
    ]."
    -2.19
    }
    
    -2.19
    祤
    -2.09
    
    -2.02
    分けて
    -1.98
     stratégie
    -1.95
     motores
    -1.94
     concentrado
    -1.91
    ajuku
    -1.89
    POSITIVE LOGITS
    </b>
    2.44
    }
    2.19
    牁
    2.08
     jaja
    1.91
    mathrm
    1.91
     <",
    1.85
    where
    1.82
    r
    1.80
    ᡴ
    1.77
    /
    1.74
    Activations Density 0.002%

    No Known Activations