© 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. 124103
    Prev
    Next
    INDEX
    Explanations

    quantity, condition, or critical element

    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
     לא
    0.48
     שלא
    0.47
    窗
    0.46
    嫋
    0.46
    要知道
    0.45
    窓
    0.44
     что
    0.43
    madı
    0.42
    ޯ
    0.42
     окна
    0.41
    POSITIVE LOGITS
    ic
    0.58
    ac
    0.57
     aquatic
    0.52
     around
    0.50
     scouting
    0.48
    anche
    0.47
     scout
    0.46
     autour
    0.45
    ical
    0.44
    ec
    0.44
    Activations Density 0.002%

    No Known Activations