© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68033
    Prev
    Next
    INDEX
    Explanations

    order item

    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
     or
    -1.01
    няли
    -0.99
    gäng
    -0.95
     chré
    -0.92
     vacancies
    -0.88
    FunctionName
    -0.88
     at
    -0.87
     and
    -0.86
    Testimonials
    -0.86
    bahnhof
    -0.85
    POSITIVE LOGITS
    FetchType
    1.27
     purchases
    1.14
     purchase
    1.13
     पुन
    1.11
    करण
    1.10
     composants
    1.09
     kvinnor
    1.09
    hagic
    1.08
     måneder
    1.07
    不是很
    1.05
    Activations Density 0.018%

    No Known Activations