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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100144
    Prev
    Next
    INDEX
    Explanations

    Turbine Reliability

    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
    5
    0.50
    8
    0.47
    سلام
    0.45
    س
    0.44
    ئ
    0.44
    <?
    0.44
    9
    0.43
    قر
    0.43
    4
    0.43
    پ
    0.43
    POSITIVE LOGITS
    とともに
    0.47
     woo
    0.46
     недалеко
    0.46
    বঙ্গের
    0.45
     verdient
    0.45
     drie
    0.45
     wooded
    0.44
    ন্তে
    0.44
     usu
    0.44
    вани
    0.43
    Activations Density 0.002%

    No Known Activations