© 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. 371
    Prev
    Next
    INDEX
    Explanations

    specific topics or entities

    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
    </b>
    -1.90
    </h1>
    -1.65
     a
    -1.49
    待遇
    -1.45
     sorta
    -1.44
    </h5>
    -1.43
    :……
    -1.41
    "};
    -1.40
    局面
    -1.38
    告知
    -1.36
    POSITIVE LOGITS
     Inglés
    1.63
    6
    1.60
    tion
    1.57
     Colección
    1.55
     zoude
    1.53
    5
    1.51
    dyti
    1.47
    뿍
    1.47
     verhind
    1.46
     AGAIN
    1.45
    Activations Density 0.003%

    No Known Activations