© 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. 65164
    Prev
    Next
    INDEX
    Explanations

    improve, reduce, expand, create

    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
    datable
    -1.42
    despite
    -1.41
     IBRARY
    -1.36
    кера
    -1.34
    titian
    -1.30
    thof
    -1.29
    cologist
    -1.29
    ₦
    -1.28
    OUTUBE
    -1.27
    tine
    -1.27
    POSITIVE LOGITS
     enormously
    1.60
    </b>
    1.60
     pertinent
    1.58
     the
    1.57
    </strong>
    1.56
     presumed
    1.55
     wildly
    1.44
     There
    1.41
    </h4>
    1.40
     написал
    1.40
    Activations Density 0.177%

    No Known Activations