© 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. 20765
    Prev
    Next
    INDEX
    Explanations

    possible installation hope remember

    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
    ֢
    -1.60
    איך
    -1.43
    However
    -1.43
     however
    -1.40
     bruker
    -1.39
    oxia
    -1.35
     nhưng
    -1.34
    lahir
    -1.32
    )--(
    -1.31
    noah
    -1.30
    POSITIVE LOGITS
    op
    1.69
     instead
    1.59
    ou
    1.52
     continually
    1.48
    om
    1.45
    _
    1.41
    ons
    1.40
    or
    1.39
    rc
    1.38
    em
    1.37
    Activations Density 0.048%

    No Known Activations