© 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. 17225
    Prev
    Next
    INDEX
    Explanations

    war, election, conflict, Changes, Competition, act

    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
    इनस
    0.55
    äten
    0.53
    <0x90>
    0.48
    ാ
    0.48
    інки
    0.47
    chränk
    0.46
     dành
    0.46
    ﻨ
    0.45
    人も
    0.44
     জন্যও
    0.44
    POSITIVE LOGITS
    :
    0.55
     continues
    0.46
     what
    0.45
    ():
    0.45
     resulted
    0.45
    ;
    0.43
     What
    0.43
     continue
    0.42
    what
    0.41
    有什么
    0.41
    Activations Density 0.050%

    No Known Activations