© 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. 99097
    Prev
    Next
    INDEX
    Explanations

    string formatting placeholders

    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
     zwi
    -2.06
     ulica
    -1.91
     musikk
    -1.91
     explicado
    -1.87
     both
    -1.87
     delicada
    -1.82
     sikker
    -1.80
    
    -1.77
     the
    -1.76
    嵎
    -1.74
    POSITIVE LOGITS
     ที่
    2.31
    同じ
    2.03
    </i>
    1.80
    铪
    1.77
    5
    1.77
    </h3>
    1.68
    </strong>
    1.66
    3
    1.62
    ving
    1.60
    PARATION
    1.59
    Activations Density 0.003%

    No Known Activations