© 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. 112812
    Prev
    Next
    INDEX
    Explanations

    past tense or discontinued

    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
    禇
    0.50
     futbol
    0.48
     हूँ
    0.48
    鵃
    0.48
    truth
    0.47
    傈
    0.46
     trauer
    0.46
    સાય
    0.46
    tìm
    0.46
    伦
    0.46
    POSITIVE LOGITS
     had
    0.52
    もあった
    0.46
     wrongly
    0.45
     недостаточно
    0.43
    ាញ
    0.43
    しかった
    0.42
     wasn
    0.42
     ceased
    0.41
     was
    0.41
     discontinued
    0.40
    Activations Density 0.006%

    No Known Activations