© 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. 67287
    Prev
    Next
    INDEX
    Explanations

    $Id tags

    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
     hidráulica
    -1.60
     adquirido
    -1.52
     habilitar
    -1.48
     regulador
    -1.48
    Those
    -1.47
     elétrica
    -1.45
     térmico
    -1.45
     erinner
    -1.42
     erklär
    -1.41
     maravillas
    -1.41
    POSITIVE LOGITS
    0
    1.52
    哽
    1.34
     of
    1.34
     sobri
    1.31
     infrar
    1.31
     uite
    1.30
     -
    1.30
    us
    1.28
    tahui
    1.27
     manier
    1.27
    Activations Density 0.038%

    No Known Activations