© 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. 93734
    Prev
    Next
    INDEX
    Explanations

    scenarios and contexts

    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
    ವುದ
    0.40
    ತಿಯ
    0.39
    τικά
    0.39
     surname
    0.39
    Addressing
    0.38
    ongyang
    0.38
    arendon
    0.37
    ̔
    0.37
    Modeling
    0.37
     terc
    0.37
    POSITIVE LOGITS
     स्वातंत्र्य
    0.50
     விளை
    0.46
     уведом
    0.46
     photosynthesis
    0.45
     extremes
    0.45
     алге
    0.45
    ுக்
    0.45
     Fehler
    0.45
     zdjęcie
    0.44
    别人
    0.43
    Activations Density 0.002%

    No Known Activations