© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8649
    Prev
    Next
    INDEX
    Explanations

    names followed by identifiers

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

    Lucy Faithful Foundation / Internet Watch Foundation / Paul Farman / Compound proportion

    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_40_width_16k_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
    英國
    0.68
     لندن
    0.63
    british
    0.61
     ব্রিটিশ
    0.59
     ব্রিটেনের
    0.57
     البريط
    0.55
     británico
    0.55
     Sólo
    0.55
    イギリス
    0.55
     ব্রিট
    0.55
    POSITIVE LOGITS
     envisaged
    0.56
     envis
    0.55
     cuba
    0.55
    thorpe
    0.54
     envisage
    0.49
     arable
    0.49
    нор
    0.49
    һ
    0.49
     sands
    0.49
    combe
    0.48
    Activations Density 0.279%

    No Known Activations