© 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. 10-GEMMASCOPE-RES-131K
    7. 105085
    Prev
    Next
    INDEX
    Explanations

    green valley, graft versus, GV films

    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
    '
    -3.41
    }
    -3.16
    }$
    -3.03
    袮
    -2.72
    鈇
    -2.66
    ↵↵
    -2.64
     This
    -2.58
    i
    -2.56
     ถ้า
    -2.42
    d
    -2.33
    POSITIVE LOGITS
    ?”
    3.13
    :”
    2.83
     rufen
    2.73
    苤
    2.69
     barata
    2.56
     derechos
    2.56
    襁
    2.56
    睥
    2.55
     preciosa
    2.53
     sagrada
    2.52
    Activations Density 0.003%

    No Known Activations