© 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-262K
    7. 10998
    Prev
    Next
    INDEX
    Explanations

    street address components

    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_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
    خوا
    0.34
    畏
    0.34
    isz
    0.33
     ulic
    0.32
     calle
    0.32
     ماند
    0.32
     Wilhelm
    0.31
    何度
    0.31
     Jl
    0.31
    wny
    0.31
    POSITIVE LOGITS
    墘
    0.42
     renters
    0.41
    مدينة
    0.40
     مدينة
    0.39
    듈
    0.39
     Epub
    0.38
     ঢাকায়
    0.37
     пів
    0.37
     міста
    0.37
     क्री
    0.37
    Activations Density 0.012%

    No Known Activations