© 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-65K
    7. 36182
    Prev
    Next
    INDEX
    Explanations

    planned it, towing will, Often starts, zoom in, section of, course file, zip file

    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_65k_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
    itous
    0.44
     multinational
    0.44
    你去
    0.44
    øre
    0.43
    textepsilon
    0.43
    زام
    0.41
     appels
    0.41
    ʔ
    0.41
     automóvil
    0.41
     تحديد
    0.41
    POSITIVE LOGITS
    <0x0D>
    0.53
    Agricultural
    0.49
     кожи
    0.49
    Champion
    0.47
    ศ
    0.46
    PhoneNumber
    0.45
    Editor
    0.45
    Org
    0.45
    ા
    0.45
    บ
    0.45
    Activations Density 0.001%

    No Known Activations