© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80685
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    あんまり
    -1.45
    おわりに
    -1.43
    美味しそう
    -1.36
     tages
    -1.27
     некоторых
    -1.23
     keinen
    -1.22
     aucune
    -1.21
    そこまで
    -1.20
    めっちゃ
    -1.20
     provi
    -1.20
    POSITIVE LOGITS
    </sub>
    1.34
    itarios
    1.23
     to
    1.21
     when
    1.20
     from
    1.20
     while
    1.16
     including
    1.16
     Also
    1.16
    </h3>
    1.15
    ));
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.