© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58041
    Prev
    Next
    INDEX
    Explanations

    thank you for your business

    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
    Ergebnisse
    -1.08
     segítség
    -0.96
     mengumumkan
    -0.95
    DeclareMath
    -0.94
     actrice
    -0.92
     início
    -0.90
     ünl
    -0.90
     inilah
    -0.90
     baratos
    -0.87
     avião
    -0.87
    POSITIVE LOGITS
     our
    1.77
     we
    1.51
     TripAdvisor
    1.47
     feedback
    1.46
     your
    1.43
     esperamos
    1.27
     customer
    1.20
     mentioned
    1.13
    Guests
    1.10
     máme
    1.09
    Activations Density 0.010%

    No Known Activations