© 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. 216595
    Prev
    Next
    INDEX
    Explanations

    regions, brands, skills, polling

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

    research and analysis

    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
     Poh
    0.49
     Oaks
    0.47
    pressure
    0.44
     Genes
    0.44
    l
    0.44
    hard
    0.42
     pressure
    0.42
     ave
    0.41
     polity
    0.41
     PropTypes
    0.41
    POSITIVE LOGITS
     Национа
    0.55
    iesią
    0.49
    <unused704>
    0.49
    㫙
    0.48
     직선
    0.48
     метода
    0.47
    ESTIC
    0.47
     analizar
    0.46
    菣
    0.46
     модели
    0.45
    Activations Density 0.000%

    No Known Activations