© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111473
    Prev
    Next
    INDEX
    Explanations

    explain concepts and categories

    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_40_width_262k_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
     Subscribe
    0.41
     transferencia
    0.40
    堡
    0.40
     tru
    0.40
     subscribed
    0.39
     charger
    0.38
    кут
    0.38
    ﹏
    0.38
     elegir
    0.37
     Subscription
    0.37
    POSITIVE LOGITS
    荲
    0.44
    ಾಟ
    0.43
     בפ
    0.43
    雦
    0.41
    ovaniyu
    0.41
    铯
    0.40
     معاملات
    0.40
    वर्धन
    0.39
    iliations
    0.38
     காட்ச
    0.38
    Activations Density 0.000%

    No Known Activations