© 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. 10-GEMMASCOPE-RES-131K
    4. 41541
    Prev
    Next
    INDEX
    Explanations

    description

    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
    だったので
    -1.46
    </h1>
    -1.45
     our
    -1.40
    的公司
    -1.39
     construcciones
    -1.37
    </h2>
    -1.35
    lacoste
    -1.34
    moschino
    -1.32
     fisuras
    -1.31
     costumbres
    -1.30
    POSITIVE LOGITS
    zett
    1.52
    zten
    1.48
    nal
    1.45
    well
    1.44
    UM
    1.42
    way
    1.42
     ansi
    1.40
    umas
    1.38
     protoimpl
    1.38
    lam
    1.37
    Activations Density 0.019%

    No Known Activations