© 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. 169904
    Prev
    Next
    INDEX
    Explanations

    Quercus suber, Cork Oak

    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
    மின்றி
    0.54
     крова
    0.54
    弑
    0.53
     по
    0.52
     кош
    0.52
     ПП
    0.52
     санк
    0.52
    InsertInt
    0.51
     поклон
    0.50
     слай
    0.50
    POSITIVE LOGITS
    0
    0.52
    an
    0.45
    yles
    0.43
     auto
    0.41
     A
    0.41
     record
    0.41
     Castle
    0.39
    )~
    0.39
     Anf
    0.39
     Esp
    0.38
    Activations Density 0.001%

    No Known Activations