© 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. 9399
    Prev
    Next
    INDEX
    Explanations

    directly to consumers

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

    French phrases with "je"

    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
     graduellement
    0.44
    雖
    0.43
    結
    0.40
    膽
    0.40
    處理
    0.40
    戦略
    0.39
    ਢ
    0.39
    頓
    0.38
    rizio
    0.38
    yat
    0.38
    POSITIVE LOGITS
    Anim
    0.56
     Anim
    0.55
    Profession
    0.50
     анима
    0.49
     piscine
    0.48
     profiss
    0.48
    Vos
    0.47
     normativa
    0.47
    Animations
    0.47
     Animations
    0.47
    Activations Density 0.114%

    No Known Activations