© 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. 11240
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    ف
    0.96
     to
    0.87
    ح
    0.83
    س
    0.82
    ش
    0.80
    การ
    0.80
    ال
    0.78
    ため
    0.76
    ق
    0.76
    ك
    0.75
    POSITIVE LOGITS
    t
    0.82
    elere
    0.68
    ческие
    0.64
    lessis
    0.63
    য়াছে
    0.61
     спасибо
    0.61
    ем
    0.61
     și
    0.60
     somm
    0.60
    oughby
    0.59
    Activations Density 0.090%

    No Known Activations