© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21025
    Prev
    Next
    INDEX
    Explanations

    reached or contacted by

    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
    Ook
    -1.59
     öv
    -1.56
     propiet
    -1.54
     anledning
    -1.48
     ciment
    -1.42
     Dosis
    -1.40
     libere
    -1.38
     minera
    -1.36
     ventre
    -1.32
     hvilke
    -1.30
    POSITIVE LOGITS
     by
    1.76
     from
    1.63
     for
    1.62
     after
    1.58
     in
    1.50
     at
    1.41
     before
    1.39
     instead
    1.35
     would
    1.34
     There
    1.34
    Activations Density 0.031%

    No Known Activations