© 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. 52867
    Prev
    Next
    INDEX
    Explanations

    list formatting or delimiters

    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
     can
    0.55
     trench
    0.55
    だ
    0.53
    dis
    0.52
     liaison
    0.49
    ди
    0.48
     handling
    0.46
     hilly
    0.46
    domestic
    0.46
    a
    0.46
    POSITIVE LOGITS
     Emails
    0.52
    טו
    0.51
    ўна
    0.50
     coval
    0.46
    ","$
    0.46
     Вя
    0.44
     Aval
    0.43
     Refunds
    0.43
     ორგანო
    0.43
    桿
    0.43
    Activations Density 0.000%

    No Known Activations