© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19925
    Prev
    Next
    INDEX
    Explanations

    installation instructions

    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
    </strong>
    -2.56
     to
    -2.06
     
    -1.90
     is
    -1.82
    </h1>
    -1.72
     you
    -1.66
    </b>
    -1.63
    </h4>
    -1.63
     of
    -1.63
    </u>
    -1.55
    POSITIVE LOGITS
     diriger
    1.96
     Ajoutez
    1.71
    They
    1.70
    瘰
    1.70
     撮っ
    1.66
     favoris
    1.66
     Ouvrez
    1.61
     Organizador
    1.61
    канал
    1.58
     ROGER
    1.53
    Activations Density 0.006%

    No Known Activations