© 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. 10-GEMMASCOPE-RES-131K
    7. 806
    Prev
    Next
    INDEX
    Explanations

    prob of picking

    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
    Lla
    -1.56
     berge
    -1.49
    </h2>
    -1.41
    ulti
    -1.38
     menyen
    -1.34
     sosi
    -1.31
     vuitton
    -1.29
     biografi
    -1.28
     ſeveral
    -1.27
    teilungen
    -1.25
    POSITIVE LOGITS
     while
    1.66
     and
    1.41
    理由は
    1.40
    There
    1.38
     from
    1.30
    ):
    1.27
    Many
    1.27
    すでに
    1.25
     has
    1.24
    borsa
    1.23
    Activations Density 0.092%

    No Known Activations