© 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. 40249
    Prev
    Next
    INDEX
    Explanations

    calendar events, aggressive behavior, code syntax

    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
    चे
    0.52
    м
    0.49
     (
    0.48
    сто
    0.48
     on
    0.46
     lama
    0.46
     конце
    0.46
    (
    0.46
     опа
    0.46
    పతి
    0.45
    POSITIVE LOGITS
    ening
    0.43
    IsNullOrEmpty
    0.43
    दिग्ध
    0.43
     ഒഴി
    0.43
    excludeFolder
    0.43
    اولة
    0.43
    怼
    0.42
    <unused240>
    0.42
    लेषण
    0.42
     TestAvg
    0.41
    Activations Density 0.001%

    No Known Activations