© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    often offer

    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
     nitrification
    0.46
    hatiti
    0.44
     qualitatively
    0.43
     radionu
    0.42
    罌
    0.41
    striées
    0.41
     rodean
    0.41
    кович
    0.40
    번에
    0.40
    idespread
    0.40
    POSITIVE LOGITS
     G
    0.51
     I
    0.50
    I
    0.49
    Acc
    0.48
    K
    0.48
    i
    0.47
    H
    0.47
    e
    0.46
    a
    0.46
    ear
    0.45
    Activations Density 0.002%

    No Known Activations