© 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. 22-GEMMASCOPE-RES-131K
    7. 40039
    Prev
    Next
    INDEX
    Explanations

    hypothetical past possibility

    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
     artık
    -0.89
     will
    -0.88
    мена
    -0.86
     konkrét
    -0.85
    jesz
    -0.84
     investissement
    -0.83
    НОСТИ
    -0.83
    urezza
    -0.81
    IkReal
    -0.80
     fournis
    -0.79
    POSITIVE LOGITS
     could
    1.77
    Could
    1.32
     hätte
    1.26
     poderia
    1.21
     könnte
    1.16
     many
    1.16
     instead
    1.13
     мог
    1.12
     könnten
    1.09
     могла
    1.09
    Activations Density 0.030%

    No Known Activations