© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72760
    Prev
    Next
    INDEX
    Explanations

    of the

    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
     они
    -1.93
     with
    -1.78
     tomaron
    -1.55
     mereka
    -1.53
    他們
    -1.49
    憫
    -1.45
     armados
    -1.44
    dhi
    -1.43
     agarre
    -1.42
     or
    -1.38
    POSITIVE LOGITS
     will
    2.33
     would
    1.85
     are
    1.71
     must
    1.61
     were
    1.52
     then
    1.47
    是很
    1.41
    ids
    1.36
     have
    1.35
     \
    1.30
    Activations Density 0.062%

    No Known Activations