© 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. 42036
    Prev
    Next
    INDEX
    Explanations

    historical context or societal bias

    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
    兘
    0.48
     került
    0.44
    ियल
    0.44
    utiérrez
    0.43
    し
    0.42
    âtel
    0.41
    餒
    0.40
    തന്ത്ര
    0.40
    うまく
    0.40
    ጠቀም
    0.40
    POSITIVE LOGITS
     Simply
    0.52
    阌
    0.50
     ट्रॉफी
    0.47
     LANA
    0.47
     Uninstall
    0.47
     bombardment
    0.45
     Gymn
    0.45
     Simplified
    0.45
     SAC
    0.44
    㓡
    0.44
    Activations Density 0.001%

    No Known Activations