© 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. 112683
    Prev
    Next
    INDEX
    Explanations

    grumble, murmur, uttered

    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
    麒麟
    -2.11
    峮
    -2.02
    曙
    -1.99
     There
    -1.93
    ména
    -1.91
    RenderAtEndOf
    -1.90
    姥
    -1.85
    五年
    -1.81
    殇
    -1.80
     }
    -1.79
    POSITIVE LOGITS
    “
    2.77
    0
    1.98
     valentín
    1.95
    .
    1.87
    5
    1.87
    的声音
    1.84
    1
    1.82
     consegue
    1.82
     handful
    1.80
    蹀
    1.78
    Activations Density 0.003%

    No Known Activations