© 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. 125562
    Prev
    Next
    INDEX
    Explanations

    urls, watches, legal cases, knowledge, strengths, next generation

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

    SM, battery, Goal

    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
    жении
    0.45
    爨
    0.43
    работка
    0.42
    鉚
    0.41
     "")
    0.41
     র‌
    0.41
    ውስ
    0.41
    setRequestHeader
    0.40
    禱
    0.40
     اخذ
    0.39
    POSITIVE LOGITS
    pathetic
    0.59
     domains
    0.54
    s
    0.54
     pumpkins
    0.52
    pumpkin
    0.51
     gasto
    0.50
     pumpkin
    0.50
     burdensome
    0.50
     silla
    0.50
    y
    0.49
    Activations Density 0.000%

    No Known Activations