© 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. 22224
    Prev
    Next
    INDEX
    Explanations

    code, html, and english words

    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
     manifiesta
    -1.58
     Dimensiones
    -1.43
     involucra
    -1.42
    
    -1.41
     смогут
    -1.41
    所以在
    -1.39
    irmanship
    -1.38
    вають
    -1.38
     навіть
    -1.37
    你了
    -1.35
    POSITIVE LOGITS
    </h2>
    1.94
     but
    1.77
    The
    1.63
    ATIVA
    1.48
    </em>
    1.46
    ASING
    1.43
    \
    1.42
    和其他
    1.40
    ATURA
    1.40
     Also
    1.38
    Activations Density 0.011%

    No Known Activations