© 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. 58997
    Prev
    Next
    INDEX
    Explanations

    we introduce information

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

    introducing an article

    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
    覺得
    0.56
    聽到
    0.52
     احتاج
    0.52
     adicionar
    0.50
    來看
    0.50
    你说
    0.49
    说道
    0.48
    짐
    0.48
    َا
    0.48
     اريد
    0.48
    POSITIVE LOGITS
    son
    0.47
     familiarity
    0.46
     biographical
    0.45
     J
    0.45
    ser
    0.44
     Robinson
    0.44
     savory
    0.44
    et
    0.42
    world
    0.42
     archaeological
    0.41
    Activations Density 0.000%

    No Known Activations