© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54833
    Prev
    Next
    INDEX
    Explanations

    common verb-complement phrases

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

    expressions of immense pain

    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
    Not in Any Lists

    No Comments

    Negative Logits
    א
    0.58
    В
    0.53
    Á
    0.52
     amelior
    0.51
    아
    0.50
    NUMBER
    0.49
    STE
    0.49
    С
    0.48
    THE
    0.48
     elevated
    0.48
    POSITIVE LOGITS
     정의역
    0.51
     يبقى
    0.46
     રંગ
    0.46
     sàng
    0.46
     거고
    0.46
    iseite
    0.45
     અથવા
    0.45
     persegi
    0.44
    roh
    0.44
     具体
    0.44
    Activations Density 0.000%

    No Known Activations