© 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. 11801
    Prev
    Next
    INDEX
    Explanations

    division by a number

    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
    ug
    0.44
     கடும்
    0.44
    athermy
    0.42
     вовсе
    0.41
    Ӏ
    0.41
     "-"]
    0.41
     ಸಾಕ
    0.40
     எடுக்க
    0.40
    <unused75>
    0.39
     ግን
    0.39
    POSITIVE LOGITS
     את
    0.55
     the
    0.55
    各种
    0.52
     doğru
    0.49
     çeşitli
    0.48
     to
    0.47
    还有
    0.46
     elemento
    0.45
    相应的
    0.45
     ihe
    0.45
    Activations Density 0.008%

    No Known Activations