© 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. 15302
    Prev
    Next
    INDEX
    Explanations

    however, introducing contrast

    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
    )
    -1.80
    </h1>
    -1.52
     любого
    -1.45
     ´
    -1.36
     industri
    -1.36
    /
    -1.34
     are
    -1.32
     This
    -1.30
     /
    -1.29
     devising
    -1.29
    POSITIVE LOGITS
    寕
    1.55
    𖤣
    1.55
     tilbud
    1.55
     dansk
    1.48
     bedeckt
    1.45
    hiva
    1.42
     aktivitet
    1.41
    </em>
    1.41
     problemer
    1.40
    *);
    1.38
    Activations Density 0.034%

    No Known Activations