© 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. 4377
    Prev
    Next
    INDEX
    Explanations

    at all

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

    phrases of emphasis or negation

    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
    воре
    0.57
    
    0.50
     oamen
    0.49
    жая
    0.49
    みんな
    0.49
    𝐵
    0.49
     څنګه
    0.48
     rectangles
    0.48
     stej
    0.48
     הע
    0.48
    POSITIVE LOGITS
    t
    0.79
     in
    0.71
    na
    0.68
    l
    0.67
     whatsoever
    0.63
    um
    0.61
    tions
    0.61
    at
    0.60
    tt
    0.60
    en
    0.59
    Activations Density 0.021%

    No Known Activations