© 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. 22-GEMMASCOPE-RES-131K
    7. 92985
    Prev
    Next
    INDEX
    Explanations

    when to ask

    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_22/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
     participer
    -1.03
     pimiento
    -1.02
     ingenu
    -1.00
     aparte
    -0.98
     Compañía
    -0.98
     recente
    -0.96
     momentary
    -0.95
     любую
    -0.92
    quickly
    -0.91
     recém
    -0.91
    POSITIVE LOGITS
     these
    1.59
     this
    1.47
     each
    1.27
     its
    1.27
     such
    1.23
     various
    1.11
     before
    1.10
     other
    1.07
     or
    1.04
     those
    1.04
    Activations Density 0.061%

    No Known Activations