© 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. 198677
    Prev
    Next
    INDEX
    Explanations

    lock, performance, compartment, son

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

    structured explanations or lists

    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
    Negative Logits
    1
    0.68
    ウ
    0.61
    у
    0.59
    ב
    0.57
    우
    0.57
    ニチ
    0.52
    보
    0.51
    гро
    0.51
    처
    0.51
    зу
    0.50
    POSITIVE LOGITS
     disediakan
    0.53
     ৭৮
    0.48
     ৫৫
    0.47
     CGPoint
    0.45
    ätte
    0.45
    ántica
    0.45
     OMB
    0.45
     SEA
    0.44
     Aquaculture
    0.44
    ServiceGroupID
    0.43
    Activations Density 0.001%

    No Known Activations