© 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. 7437
    Prev
    Next
    INDEX
    Explanations

    changes and actions

    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
    اموش
    0.46
    لې
    0.40
    ڭ
    0.40
    崙
    0.39
     laryng
    0.39
     savun
    0.38
     nossas
    0.38
     Anci
    0.38
     رون
    0.38
    HomePage
    0.37
    POSITIVE LOGITS
     আমেরিকার
    0.39
    ิ่น
    0.37
    民
    0.37
    所属
    0.37
     dwells
    0.37
     intends
    0.37
     freely
    0.36
     বাস্তব
    0.36
    민
    0.36
     유
    0.36
    Activations Density 0.003%

    No Known Activations