© 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. 31-GEMMASCOPE-2-RES-262K
    7. 51273
    Prev
    Next
    INDEX
    Explanations

    Gemma model description

    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_31_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
    桠
    0.45
    
    0.45
     кнопки
    0.44
    с
    0.44
    sigh
    0.44
    шли
    0.43
     политики
    0.43
     ули
    0.42
    ллин
    0.42
    т
    0.42
    POSITIVE LOGITS
     includes
    0.52
     Eight
    0.50
     epidemiological
    0.49
     postice
    0.49
     Prosecution
    0.47
     Tuberculosis
    0.45
     Preface
    0.45
     epidemi
    0.45
     Following
    0.44
     listens
    0.44
    Activations Density 0.001%

    No Known Activations