© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9073
    Prev
    Next
    INDEX
    Explanations

    reverse proxy

    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_16_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
    haut
    0.50
    리를
    0.48
    feeds
    0.47
    готовка
    0.46
    鶘
    0.46
    feed
    0.45
    ંકી
    0.45
     Politiker
    0.44
    ⍵
    0.44
    формация
    0.43
    POSITIVE LOGITS
    ت
    0.53
    т
    0.48
     mora
    0.48
    ığımız
    0.45
    त
    0.45
     movement
    0.45
     дър
    0.45
     large
    0.44
     metre
    0.44
     monochromatic
    0.44
    Activations Density 0.000%

    No Known Activations