© 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. 71961
    Prev
    Next
    INDEX
    Explanations

    words like for, if, and effective

    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
    r
    0.47
    a
    0.47
    ਫ
    0.46
    Си
    0.46
    測
    0.45
     SERVER
    0.44
     yil
    0.42
    след
    0.41
     सर्
    0.40
    джи
    0.40
    POSITIVE LOGITS
     dilutions
    0.46
    Autoresizing
    0.44
     هایی
    0.44
    ColumnKind
    0.43
    няў
    0.43
    াহরণ
    0.42
     refinements
    0.42
     شف
    0.41
    relsen
    0.41
    㨁
    0.41
    Activations Density 0.001%

    No Known Activations