© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104601
    Prev
    Next
    INDEX
    Explanations

    start button, Driver Seat, backlit keyboard

    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
     Bemerkungen
    -1.26
     to
    -1.22
     Obwohl
    -1.20
    甚至是
    -1.19
     Vielleicht
    -1.17
     its
    -1.17
    に行ってきました
    -1.17
    我先
    -1.16
    şiv
    -1.16
     Embora
    -1.15
    POSITIVE LOGITS
     with
    1.30
     gomez
    1.23
     interieur
    1.18
     högre
    1.18
     saisons
    1.17
    fohlen
    1.17
     you
    1.15
     jule
    1.14
     tzu
    1.12
     pedro
    1.09
    Activations Density 0.003%

    No Known Activations