© 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. 195345
    Prev
    Next
    INDEX
    Explanations

    sampling with replacement

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

    probability and conditional reasoning

    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
    ိ
    0.44
     сом
    0.42
    ẹp
    0.41
     группы
    0.41
     pyramidal
    0.40
     symmetry
    0.40
     قالب
    0.38
    蓍
    0.38
     juni
    0.38
     Contents
    0.38
    POSITIVE LOGITS
    attended
    0.46
    pipeline
    0.46
    watched
    0.45
    field
    0.45
    industry
    0.45
    independence
    0.44
    breakfast
    0.44
    independent
    0.44
    ebay
    0.43
    fetch
    0.43
    Activations Density 0.004%

    No Known Activations