© 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. 48821
    Prev
    Next
    INDEX
    Explanations

    implied or assumed

    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
     phénom
    0.44
     juu
    0.42
     عائد
    0.42
    誒
    0.42
    executer
    0.41
     вона
    0.41
     Wohnung
    0.40
    llam
    0.40
    閁
    0.39
     ahora
    0.39
    POSITIVE LOGITS
    计数
    0.44
    ёз
    0.43
     ев
    0.43
    引进
    0.43
     aastal
    0.43
    ри
    0.41
     four
    0.40
     renewals
    0.40
    4
    0.40
    ători
    0.38
    Activations Density 0.007%

    No Known Activations