© 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. 36386
    Prev
    Next
    INDEX
    Explanations

    research group project career network

    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
     are
    -1.57
    or
    -1.33
     have
    -1.30
    </h1>
    -1.27
     of
    -1.27
    on
    -1.26
    we
    -1.25
    of
    -1.23
    is
    -1.21
    as
    -1.21
    POSITIVE LOGITS
     and
    1.45
    نیم
    1.37
     verdieping
    1.35
     illustratie
    1.34
    anmar
    1.33
     일본
    1.30
    pasti
    1.30
     bicicletas
    1.27
     여자
    1.27
     hjemmes
    1.27
    Activations Density 0.107%

    No Known Activations