© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2622
    Prev
    Next
    INDEX
    Explanations

    SQL data types and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    觥
    0.72
    rounds
    0.64
     feasts
    0.61
     unnoticed
    0.61
    progress
    0.59
    grids
    0.58
     rounding
    0.58
     쌓
    0.56
    scroll
    0.55
     affairs
    0.55
    POSITIVE LOGITS
     модель
    2.07
     характеристи
    1.99
     модели
    1.95
    audioType
    1.95
     modellen
    1.92
     نموذج
    1.92
     qualités
    1.91
     personnage
    1.89
     объекта
    1.88
     характеристики
    1.88
    Activations Density 0.089%

    No Known Activations