© 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. 40653
    Prev
    Next
    INDEX
    Explanations

    lines and numbers

    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
     મે
    0.45
     घोष
    0.45
    jskiej
    0.44
     boxer
    0.44
     skiers
    0.43
    鮒
    0.42
    इंट
    0.42
     idk
    0.42
     ដ
    0.41
     odmah
    0.41
    POSITIVE LOGITS
    Processes
    0.46
    碎片
    0.45
    Dedicated
    0.45
    ть
    0.44
    Standalone
    0.43
    шения
    0.42
    رات
    0.41
     наві
    0.41
    ار
    0.41
    Entertainment
    0.40
    Activations Density 0.002%

    No Known Activations