© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    specifications or contexts

    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
     puisqu
    0.40
     this
    0.40
     {//
    0.38
    prefixes
    0.38
     postes
    0.37
     signification
    0.37
     meaning
    0.37
     '%'
    0.37
     designating
    0.36
     usages
    0.36
    POSITIVE LOGITS
    且
    1.10
    而且
    1.00
    しかも
    0.92
    并且
    0.85
     עם
    0.82
    並且
    0.81
     而且
    0.81
    かつ
    0.77
    Moreover
    0.70
     with
    0.68
    Activations Density 0.249%

    No Known Activations