© 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. 119644
    Prev
    Next
    INDEX
    Explanations

    initial expressions

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

    knows if

    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
    Ī
    0.57
     equip
    0.52
    𝟐
    0.48
     &/
    0.47
     interchanges
    0.46
    ↔
    0.46
    Ĭ
    0.46
    सीएल
    0.46
    IPV
    0.45
     insufficiency
    0.45
    POSITIVE LOGITS
     absolutamente
    0.50
    ત્તા
    0.47
    anyone
    0.47
    absolutely
    0.47
    只是
    0.47
    仿佛
    0.46
     itulah
    0.45
     다만
    0.45
    宦
    0.44
    这是
    0.44
    Activations Density 0.001%

    No Known Activations