© 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. 183083
    Prev
    Next
    INDEX
    Explanations

    does NOT

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

    already experienced sensitive

    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
    ០
    0.48
     gesture
    0.47
     wor
    0.47
     rules
    0.45
    ອ
    0.45
    にある
    0.44
    悪
    0.44
     gameOver
    0.43
     governance
    0.43
     aturan
    0.43
    POSITIVE LOGITS
     Technologien
    0.45
     Vgl
    0.45
     Monaten
    0.43
    were
    0.42
     பல்கலை
    0.42
     Taş
    0.41
     formada
    0.41
     Monuments
    0.41
    ственных
    0.40
    :")
    0.40
    Activations Density 0.000%

    No Known Activations