© 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. 75673
    Prev
    Next
    INDEX
    Explanations

    subdivision one

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

    potentially sensitive or harmful

    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
    搛
    0.45
     previews
    0.45
     interferometer
    0.45
     preacher
    0.44
     gages
    0.44
     anvil
    0.43
     scru
    0.43
     preview
    0.42
     carefully
    0.42
     való
    0.42
    POSITIVE LOGITS
    ש
    0.56
    ك
    0.51
     Allah
    0.49
    我
    0.49
    ﮗ
    0.49
    芾
    0.48
    ץ
    0.48
    ফ
    0.47
     Rhythm
    0.47
     politische
    0.47
    Activations Density 0.001%

    No Known Activations