© 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. 199924
    Prev
    Next
    INDEX
    Explanations

    indicated, ©, year, option

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

    Chinese/Confucian philosophy

    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
     transitions
    0.48
     nämlich
    0.48
     émissions
    0.48
    werden
    0.47
     მნიშვნელ
    0.45
     إ
    0.45
     verlieren
    0.44
     হয়
    0.44
     γ
    0.44
     μο
    0.44
    POSITIVE LOGITS
    Ŋ
    0.47
    🤵
    0.47
    빈
    0.46
    adapter
    0.46
     avar
    0.46
    soph
    0.45
    abhavam
    0.44
    luxury
    0.44
     계획
    0.43
     Bingo
    0.43
    Activations Density 0.000%

    No Known Activations