© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206006
    Prev
    Next
    INDEX
    Explanations

    creatures happy, lifetime costs

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

    incredibly inefficient

    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
    ラ
    0.60
    淵
    0.57
     curviliné
    0.55
    ᛁ
    0.55
    ラの
    0.53
     instinctively
    0.52
     запах
    0.52
     истины
    0.51
    叕
    0.51
     канали
    0.50
    POSITIVE LOGITS
    ↵
    0.55
    ’.
    0.52
    entry
    0.50
    。
    0.47
     charge
    0.44
    na
    0.43
    mon
    0.43
    ’,
    0.42
     entry
    0.42
    query
    0.42
    Activations Density 0.000%

    No Known Activations