© 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. 167798
    Prev
    Next
    INDEX
    Explanations

    specific contexts

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

    very rough or vim command

    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
     Yu
    0.50
    ③
    0.49
     হইবে
    0.47
     বলিতে
    0.47
     Lee
    0.46
    猪
    0.46
    ASI
    0.46
     Developmental
    0.46
    сів
    0.46
     diperoleh
    0.45
    POSITIVE LOGITS
     refres
    0.48
     refreshed
    0.48
    ća
    0.46
    nica
    0.45
     /></
    0.44
    uose
    0.44
    irable
    0.44
     მიმოწერა
    0.44
    뒹
    0.43
    sair
    0.43
    Activations Density 0.000%

    No Known Activations