© 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. 40-GEMMASCOPE-2-RES-65K
    7. 782
    Prev
    Next
    INDEX
    Explanations

    there once was a / win an award

    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_40_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
    ச்
    0.36
     recombinant
    0.30
     putative
    0.29
     EGFR
    0.29
    }\,\
    0.28
     HIV
    0.28
     collaborators
    0.27
     COVID
    0.27
    :
    0.27
     combinatorial
    0.27
    POSITIVE LOGITS
     إذا
    0.38
     Якщо
    0.37
     якщо
    0.35
    饮料
    0.34
     รี
    0.33
    璈
    0.32
    ߋ
    0.32
    当你
    0.32
    糇
    0.32
    曛
    0.32
    Activations Density 0.011%

    No Known Activations