© 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. 168455
    Prev
    Next
    INDEX
    Explanations

    accept, receive, hear, endure

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

    closing positions

    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
    पह
    0.46
    产能
    0.45
    ρ
    0.45
    ีย
    0.43
    rs
    0.40
    elect
    0.40
    eof
    0.40
    芻
    0.39
    r
    0.39
    𝙧
    0.38
    POSITIVE LOGITS
     drzew
    0.53
     giardino
    0.51
     dieu
    0.51
     儿童
    0.50
     खोज
    0.49
     marzo
    0.49
     pranzo
    0.48
     dziecko
    0.48
     이라고
    0.48
     結婚
    0.48
    Activations Density 0.001%

    No Known Activations