© 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. 25590
    Prev
    Next
    INDEX
    Explanations

    universal followed by specific contexts

    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
    Ww
    -1.05
    botas
    -1.02
     testemun
    -1.00
    EES
    -0.99
     sturdy
    -0.97
     tiennent
    -0.96
     quintessential
    -0.96
     Ngoài
    -0.96
    OTHERS
    -0.95
     insanely
    -0.94
    POSITIVE LOGITS
    Universal
    1.57
     universal
    1.55
     Universal
    1.55
    universal
    1.49
     suffrage
    1.34
     Studios
    1.23
     UNIVERSAL
    1.16
     universally
    1.13
     studios
    1.06
    Just
    1.04
    Activations Density 0.015%

    No Known Activations