© 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. 121755
    Prev
    Next
    INDEX
    Explanations

    without risks

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

    AI mentor assistance

    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
    瀑
    0.43
    兔子
    0.42
    slick
    0.42
    嗥
    0.41
     řek
    0.41
    odd
    0.41
     planta
    0.41
     Stet
    0.41
     ROOM
    0.41
     Rochelle
    0.40
    POSITIVE LOGITS
     kidnap
    0.58
     apologise
    0.54
     đừng
    0.48
     ayudarte
    0.48
     поможет
    0.48
     هناخد
    0.48
    ມ
    0.48
     مزید
    0.47
     risking
    0.47
    т
    0.47
    Activations Density 0.001%

    No Known Activations