© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40415
    Prev
    Next
    INDEX
    Explanations

    May Contain, which translates

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

    analyzing or manipulating actions

    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
     varios
    0.55
    LY
    0.50
    কারে
    0.50
    یت
    0.50
    ੴ
    0.48
     grocery
    0.47
     veloce
    0.47
     valori
    0.47
    weets
    0.46
     obicei
    0.46
    POSITIVE LOGITS
     בכ
    0.50
    的时
    0.45
    tiempo
    0.45
    鐪
    0.44
     أع
    0.43
    timeouts
    0.43
     بيد
    0.43
     هن
    0.42
    getTime
    0.42
    جلس
    0.42
    Activations Density 0.000%

    No Known Activations