© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65960
    Prev
    Next
    INDEX
    Explanations

    counting discrete items

    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
     and
    -1.48
    ₱
    -1.41
     både
    -1.39
     either
    -1.38
     them
    -1.38
    domada
    -1.37
    <h2>
    -1.36
    POSE
    -1.36
    valently
    -1.33
    ˂
    -1.33
    POSITIVE LOGITS
     cristo
    1.29
     仕様
    1.27
     nyelv
    1.27
     VIDEOT
    1.27
     JOSÉ
    1.22
     pimiento
    1.22
     Informe
    1.19
     Сколько
    1.18
     tunn
    1.17
     JUAN
    1.16
    Activations Density 0.031%

    No Known Activations