© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59763
    Prev
    Next
    INDEX
    Explanations

    lossless encoder, sign on, Hedy Lamarr

    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
     you
    -1.92
     your
    -1.63
     even
    -1.58
     either
    -1.53
    了好
    -1.35
    te
    -1.34
     даже
    -1.27
     anyone
    -1.25
    to
    -1.24
     them
    -1.24
    POSITIVE LOGITS
    </sub>
    1.56
    Garantie
    1.38
     recomendable
    1.38
    UNIDENTIFIED
    1.34
     Bolívar
    1.34
    schra
    1.32
    ıyoruz
    1.30
    小行星
    1.27
    痿
    1.27
     กล่อง
    1.23
    Activations Density 0.113%

    No Known Activations