© 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. 11201
    Prev
    Next
    INDEX
    Explanations

    practice followed by activity

    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
     המת
    0.64
    taine
    0.64
     spectator
    0.63
    పో
    0.62
     полу
    0.61
     ו
    0.59
     〢
    0.59
     PARTY
    0.59
     thẳng
    0.59
     thei
    0.57
    POSITIVE LOGITS
    ي
    1.28
    ب
    1.07
    يء
    1.02
    ر
    1.00
    s
    0.93
    ه
    0.92
    ات
    0.92
    ن
    0.91
    י
    0.90
    د
    0.87
    Activations Density 0.037%

    No Known Activations