© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205443
    Prev
    Next
    INDEX
    Explanations

    modelmodels, controllers, and repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scheduler
    0.42
     Komponenten
    0.40
     minor
    0.38
     ck
    0.38
    cessing
    0.38
    Min
    0.37
    स्पति
    0.37
    谑
    0.37
     Phosphorus
    0.37
     Min
    0.37
    POSITIVE LOGITS
    模型
    0.48
    모델
    0.44
    transformer
    0.43
    repository
    0.43
     repository
    0.42
     repositorio
    0.40
     презен
    0.40
     MODELS
    0.40
     modele
    0.40
    transformers
    0.39
    Activations Density 0.001%

    No Known Activations