© 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. 8778
    Prev
    Next
    INDEX
    Explanations

    position and offset

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

    location and position

    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
     &,
    0.42
    jent
    0.42
     Abelian
    0.39
     sukham
    0.37
    漓
    0.37
    elize
    0.36
     reorganized
    0.35
     "?"]
    0.35
     esclare
    0.35
    iteta
    0.35
    POSITIVE LOGITS
     центру
    0.52
    posX
    0.48
    setPosition
    0.47
    offsetLeft
    0.47
    translateX
    0.46
    offsetTop
    0.46
     центром
    0.45
    UIS
    0.45
    の位置
    0.45
     центр
    0.44
    Activations Density 0.020%

    No Known Activations