© 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. 144128
    Prev
    Next
    INDEX
    Explanations

    reasonable efforts or measures

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

    absorbed, shares, complex

    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
     flavour
    0.43
     sorg
    0.43
     prist
    0.43
     shade
    0.42
     indice
    0.42
     tempt
    0.41
    一種
    0.40
    ת
    0.40
     decad
    0.40
     tranquill
    0.40
    POSITIVE LOGITS
     ऑग
    0.52
     কমপ্লে
    0.50
    leased
    0.48
    propag
    0.47
    hauled
    0.47
    struck
    0.46
    supporting
    0.46
    classed
    0.46
    planted
    0.46
    complex
    0.46
    Activations Density 0.001%

    No Known Activations