© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39778
    Prev
    Next
    INDEX
    Explanations

    reasoning or consequence conjunctions

    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
    ?」
    -2.70
    </th>
    -2.52
    </b>
    -2.38
    "},
    -2.36
     Gedanke
    -2.31
    </i>
    -2.22
    躂
    -2.22
    "}
    -2.22
    ープン
    -2.20
    趼
    -2.20
    POSITIVE LOGITS
    '
    2.39
     poupée
    2.38
     licorne
    2.34
    </h2>
    2.25
     visst
    2.17
    찻
    2.16
    mpagne
    2.14
     odeur
    2.13
    寕
    2.11
     買
    2.09
    Activations Density 0.002%

    No Known Activations