© 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. 113285
    Prev
    Next
    INDEX
    Explanations

    Coconut Queen, Mondini

    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
    s
    -2.03
    <
    -1.67
    >
    -1.64
    \
    -1.59
    '
    -1.52
    》、《
    -1.45
     maio
    -1.41
     oktober
    -1.40
    </h4>
    -1.40
    </b>
    -1.39
    POSITIVE LOGITS
     we
    1.91
    𖣘
    1.82
    lusconi
    1.78
     descriptions
    1.65
    Ꮟ
    1.63
    ۉ
    1.61
    ↵
    1.58
     ᾿
    1.52
     financiamiento
    1.50
     wußte
    1.50
    Activations Density 0.008%

    No Known Activations