© 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. 11723
    Prev
    Next
    INDEX
    Explanations

    manage security delete account

    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
    пон
    0.42
    뀌
    0.42
     событий
    0.41
     Arithmetic
    0.41
    segmented
    0.41
     Rami
    0.39
     गणित
    0.39
     završ
    0.39
     selection
    0.39
    selection
    0.39
    POSITIVE LOGITS
     deactivate
    0.48
     protest
    0.45
     unhappy
    0.45
     defamatory
    0.45
     defamation
    0.44
    抑
    0.43
     dyslexia
    0.43
     wondered
    0.43
     unhappiness
    0.42
    逾
    0.42
    Activations Density 0.045%

    No Known Activations