© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84772
    Prev
    Next
    INDEX
    Explanations

    new internet phenomena

    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
    ATING
    0.47
    онов
    0.46
    antaranya
    0.46
    વાર
    0.45
    লিখ
    0.45
    ajati
    0.44
    offer
    0.44
    𝙙
    0.44
    ativamente
    0.43
    automobile
    0.43
    POSITIVE LOGITS
     nella
    0.55
     Shang
    0.53
     nell
    0.51
     comté
    0.49
     nesta
    0.48
     pom
    0.48
     Beit
    0.47
     cinq
    0.47
     mél
    0.47
     mozzarella
    0.47
    Activations Density 0.002%

    No Known Activations