© 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. 5867
    Prev
    Next
    INDEX
    Explanations

    conversation between

    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
     reorgan
    0.56
     indef
    0.50
    ancements
    0.50
    cción
    0.49
    了一
    0.48
    repet
    0.48
    㽡
    0.48
    ín
    0.48
     alej
    0.48
    igen
    0.47
    POSITIVE LOGITS
     between
    1.19
     між
    1.12
     بین
    1.06
     μεταξύ
    1.03
     между
    1.01
    between
    0.98
     giữa
    0.98
    Between
    0.95
     بين
    0.93
     zwischen
    0.93
    Activations Density 0.295%

    No Known Activations