© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65920
    Prev
    Next
    INDEX
    Explanations

    example of

    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
    Markt
    -1.48
    Libros
    -1.44
    ATIONS
    -1.42
    pantaloni
    -1.34
    Contexte
    -1.33
    Produktion
    -1.33
    Directeur
    -1.27
    Compati
    -1.26
    Spes
    -1.24
     atriz
    -1.23
    POSITIVE LOGITS
     but
    2.06
    </strong>
    1.65
    }
    1.63
    </h2>
    1.61
     already
    1.57
     of
    1.55
    </h1>
    1.54
    )
    1.45
    .
    1.34
    ')";
    1.31
    Activations Density 0.062%

    No Known Activations