© 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. 48817
    Prev
    Next
    INDEX
    Explanations

    numbers, fractions, and measurements

    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
    et
    0.46
    快速
    0.44
    Movie
    0.43
    вла
    0.42
     měst
    0.41
     royalty
    0.41
    ($
    0.41
    Business
    0.41
    Largest
    0.40
    Village
    0.40
    POSITIVE LOGITS
     carénés
    0.55
     nematodes
    0.52
    迠
    0.52
    chaoxing
    0.51
     myocytes
    0.51
    arettes
    0.50
    寅
    0.50
     prostaglandins
    0.49
     centimetres
    0.49
     earths
    0.48
    Activations Density 0.004%

    No Known Activations