© 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. 7092
    Prev
    Next
    INDEX
    Explanations

    heaven, sky, and places

    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
    8
    -2.19
    9
    -2.17
    </strong>
    -2.09
    0
    -2.02
    3
    -1.95
    2
    -1.87
    7
    -1.85
     électriques
    -1.68
    6
    -1.63
     gezogen
    -1.63
    POSITIVE LOGITS
     a
    2.67
     you
    2.66
    .
    1.88
    ка
    1.87
     curtail
    1.75
    ኵ
    1.70
     averiguar
    1.69
     fortalecer
    1.68
    --]
    1.66
     It
    1.65
    Activations Density 0.004%

    No Known Activations