© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27652
    Prev
    Next
    INDEX
    Explanations

    intent classification

    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_22/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
     Einleitung
    -1.13
     Monday
    -1.13
     vieler
    -1.09
     katholischen
    -1.09
     dichas
    -1.06
     too
    -1.04
     They
    -1.02
     éstos
    -1.01
     Verfasser
    -1.00
     last
    -0.99
    POSITIVE LOGITS
     LastName
    1.28
     garcía
    1.27
     LIRE
    1.20
    veis
    1.17
     minY
    1.16
     BEACH
    1.15
     alfab
    1.10
    verns
    1.10
     pán
    1.09
     Agung
    1.09
    Activations Density 0.009%

    No Known Activations