© 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. 101007
    Prev
    Next
    INDEX
    Explanations

    Formal opening of parliament

    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
    報導
    0.48
     eigens
    0.45
    وري
    0.44
     Giveen
    0.44
     profondément
    0.44
     zusätzlich
    0.44
     eigene
    0.44
    粈
    0.43
    განიზ
    0.42
    вані
    0.41
    POSITIVE LOGITS
    은
    0.57
     would
    0.50
    k
    0.48
     :
    0.48
    tra
    0.47
    는
    0.46
     is
    0.45
    params
    0.43
     Tra
    0.43
    entra
    0.43
    Activations Density 0.007%

    No Known Activations