© 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. 142486
    Prev
    Next
    INDEX
    Explanations

    wash separately

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

    patience for instructions

    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
    akn
    0.47
    羮
    0.45
    讲述
    0.45
    文學
    0.44
    ̖
    0.44
    मूल
    0.44
    ऱ्यावर
    0.44
    atter
    0.43
    爱好
    0.43
    鏢
    0.43
    POSITIVE LOGITS
     disseminated
    0.53
     breaches
    0.52
     this
    0.47
     placé
    0.46
     may
    0.45
     remove
    0.44
     přes
    0.44
     waiting
    0.44
     breached
    0.44
     expiring
    0.44
    Activations Density 0.000%

    No Known Activations