© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204939
    Prev
    Next
    INDEX
    Explanations

    riddles and explanations

    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
    alloy
    0.48
     बीएसटीसी
    0.45
     ফর
    0.44
    其中包括
    0.44
     പദ്ധതി
    0.44
     டே
    0.44
     डेफिनेशन
    0.44
    綑
    0.43
     knuckle
    0.43
     गेट
    0.43
    POSITIVE LOGITS
     sendiri
    0.52
    健康
    0.48
    수
    0.47
     hasn
    0.47
     dissolved
    0.45
     saúde
    0.45
    수를
    0.44
    自分の
    0.43
     própria
    0.42
    쁨
    0.41
    Activations Density 0.004%

    No Known Activations