© 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. 21226
    Prev
    Next
    INDEX
    Explanations

    elevator installation and systems

    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
    葑
    -1.53
    Diseño
    -1.53
    gruß
    -1.52
    CAPÍTULO
    -1.49
    菔
    -1.48
     Gruß
    -1.46
     esigen
    -1.46
    ený
    -1.45
    $_(
    -1.45
     शुर
    -1.43
    POSITIVE LOGITS
    隳
    1.66
     fass
    1.63
     grava
    1.57
     ukrain
    1.51
     frein
    1.50
    </i>
    1.49
     remplissage
    1.45
     orar
    1.44
    山的
    1.43
     decorativa
    1.42
    Activations Density 0.005%

    No Known Activations