© 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-65K
    7. 48287
    Prev
    Next
    INDEX
    Explanations

    versions and GPT models

    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_65k_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
    é
    0.54
    are
    0.52
    inner
    0.52
    k
    0.52
    key
    0.51
    Key
    0.49
    ni
    0.49
    alis
    0.49
    rio
    0.48
    achi
    0.48
    POSITIVE LOGITS
     Ừ
    0.47
     sản
    0.47
     écrite
    0.46
     puesta
    0.44
     ಸಂಗ
    0.44
     উত্প
    0.44
     tuyển
    0.43
     Mavic
    0.43
     ಸಾಮಾನ್ಯ
    0.43
    둰
    0.43
    Activations Density 0.006%

    No Known Activations