© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    subcaption or split

    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
    性和
    0.43
     قرآن
    0.43
    olecules
    0.42
    정과
    0.42
     molécules
    0.41
     及び
    0.41
    числи
    0.40
    熒
    0.40
    脤
    0.40
    횽
    0.39
    POSITIVE LOGITS
     Go
    0.48
     departmental
    0.44
     Philadelphia
    0.43
     Explore
    0.43
     Electricity
    0.43
     W
    0.42
     submerged
    0.42
     Ripple
    0.42
     onDestroy
    0.41
     ancho
    0.41
    Activations Density 0.001%

    No Known Activations