© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12066
    Prev
    Next
    INDEX
    Explanations

    numbers in meters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صارفین
    0.42
    🏇
    0.41
    Amplitude
    0.40
     chua
    0.40
    чках
    0.39
    ⊟
    0.39
     amplitude
    0.38
     Amplitude
    0.38
    ⚙
    0.38
    薷
    0.38
    POSITIVE LOGITS
    LoggerFactory
    0.54
     skor
    0.38
    好吃
    0.37
     Rek
    0.36
    SF
    0.35
    拏
    0.35
     glories
    0.34
     cal
    0.34
    Rek
    0.34
    嵐
    0.34
    Activations Density 0.002%

    No Known Activations