© 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. 34-GEMMASCOPE-RES-131K
    7. 98909
    Prev
    Next
    INDEX
    Explanations

    at specific points or conditions

    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_34/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
     at
    -1.24
    Utils
    -0.93
    ensä
    -0.89
    ometr
    -0.85
     pamphlets
    -0.82
    zione
    -0.80
    ika
    -0.80
    зоры
    -0.79
    紡
    -0.79
    斧
    -0.78
    POSITIVE LOGITS
     sites
    1.03
     above
    0.94
     chuva
    0.92
     varying
    0.90
     Site
    0.89
     einiger
    0.88
     Sites
    0.88
     vecka
    0.88
     various
    0.86
     locations
    0.86
    Activations Density 0.120%

    No Known Activations