© 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. 129369
    Prev
    Next
    INDEX
    Explanations

    describing property features

    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
    4
    -1.56
     of
    -1.45
     for
    -1.44
    5
    -1.44
    ymce
    -1.32
    8
    -1.23
    或
    -1.20
     countries
    -1.16
    6
    -1.15
     different
    -1.13
    POSITIVE LOGITS
     gede
    1.37
     restant
    1.34
     waardoor
    1.34
     groet
    1.33
    gings
    1.31
     Ży
    1.30
     paie
    1.29
    ❋
    1.29
    aians
    1.27
    ⻓
    1.27
    Activations Density 0.045%

    No Known Activations