© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28385
    Prev
    Next
    INDEX
    Explanations

    international consultancies, collecting popular

    np_acts-logits-general · gemini-2.5-flash-lite

    title, labels, or fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aita
    0.52
     Energies
    0.52
    aundice
    0.51
     Holds
    0.50
    瞇
    0.50
    해요
    0.49
    ition
    0.48
     Again
    0.48
     hereof
    0.48
    ospace
    0.47
    POSITIVE LOGITS
    Quantidade
    0.46
    Ligações
    0.43
     ferocious
    0.42
     நி
    0.41
    Cantidad
    0.41
     periodistas
    0.40
     சங்க
    0.40
     ট
    0.40
     potencia
    0.39
    Michele
    0.39
    Activations Density 0.001%

    No Known Activations