© 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. 11576
    Prev
    Next
    INDEX
    Explanations

    mathematical methods and algorithms

    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
    obedience
    0.44
    northern
    0.42
    lake
    0.42
    cook
    0.41
    offensive
    0.41
    opportunity
    0.41
    ز
    0.39
    кау
    0.38
    ingredients
    0.38
    political
    0.38
    POSITIVE LOGITS
     или
    0.45
     আলোচনা
    0.44
     français
    0.43
     постепенно
    0.42
     código
    0.42
    数学
    0.42
     чер
    0.42
    ,
    0.41
     matemático
    0.41
    ."),
    0.40
    Activations Density 0.006%

    No Known Activations