© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130999
    Prev
    Next
    INDEX
    Explanations

    initializations for member

    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
     (
    -1.36
    There
    -1.31
     That
    -1.23
    Because
    -1.23
     There
    -1.20
    You
    -1.20
     after
    -1.18
     Those
    -1.16
     eight
    -1.13
     you
    -1.12
    POSITIVE LOGITS
    0
    1.31
     rimb
    1.30
     divertimento
    1.27
    絰
    1.24
     devast
    1.23
     sicherzustellen
    1.23
     vanta
    1.21
    Nationale
    1.20
     artific
    1.19
     gita
    1.13
    Activations Density 0.012%

    No Known Activations