© 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. 11702
    Prev
    Next
    INDEX
    Explanations

    php code comments

    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
    WMat
    0.46
    埙
    0.46
    ꒪
    0.46
     WindowStateType
    0.43
    ܂
    0.43
    에서의
    0.43
     Woodson
    0.42
    য়দ
    0.41
    
    0.41
    🙎
    0.41
    POSITIVE LOGITS
     in
    0.49
     once
    0.48
    ok
    0.46
     be
    0.45
    yd
    0.44
    s
    0.44
    if
    0.42
     conference
    0.42
     change
    0.42
    run
    0.42
    Activations Density 0.001%

    No Known Activations