© 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. 44744
    Prev
    Next
    INDEX
    Explanations

    SQL operations and Python keywords

    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
    取
    0.42
     needed
    0.41
     plasm
    0.40
     magnetic
    0.40
    磁
    0.40
     counter
    0.39
     replacements
    0.39
    *
    0.39
    索
    0.39
    （
    0.38
    POSITIVE LOGITS
    aság
    0.47
    ഷേ
    0.42
    ുമെന്ന്
    0.41
    ۲
    0.40
     setError
    0.40
    ന്റ്
    0.39
     diversité
    0.39
    <unused733>
    0.39
    <unused1029>
    0.39
    /${
    0.39
    Activations Density 0.000%

    No Known Activations