© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40192
    Prev
    Next
    INDEX
    Explanations

    Fix: hide button

    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_31_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
     a
    0.50
     Fisheries
    0.46
     excellent
    0.45
     Royal
    0.42
     enhanced
    0.41
     ROYAL
    0.41
     poderoso
    0.40
     to
    0.40
     Provider
    0.40
     powerful
    0.39
    POSITIVE LOGITS
    mods
    0.50
    candles
    0.47
     সেসব
    0.46
    บาง
    0.46
    😑
    0.46
    patches
    0.44
     плохо
    0.43
     niektó
    0.43
     それぞれ
    0.43
     растения
    0.42
    Activations Density 0.002%

    No Known Activations