© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9482
    Prev
    Next
    INDEX
    Explanations

    со + word stem

    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_53_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
    桢
    0.44
    两
    0.43
     pubb
    0.42
    splunk
    0.41
    ၅
    0.40
     könnt
    0.40
     myth
    0.39
     Kijk
    0.39
    鞏
    0.39
     comen
    0.39
    POSITIVE LOGITS
     временем
    0.70
    чета
    0.58
    стояние
    0.58
    фия
    0.56
    ревнова
    0.54
    всем
    0.53
    ставля
    0.53
    вест
    0.52
    ответ
    0.52
    став
    0.51
    Activations Density 0.003%

    No Known Activations