© 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. 51486
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    \"
    0.47
    ר
    0.47
    of
    0.46
     '
    0.44
    >
    0.44
    ર
    0.44
    families
    0.43
    "
    0.43
    ),
    0.43
    changed
    0.43
    POSITIVE LOGITS
    鍝
    0.51
     converging
    0.48
    গি
    0.47
     tropomyosin
    0.47
     converges
    0.46
     ఫలి
    0.46
    thrombin
    0.45
     pumps
    0.45
     marin
    0.45
     thảo
    0.44
    Activations Density 0.000%

    No Known Activations