© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    individual blame

    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
    চো
    0.46
    Countryside
    0.44
    Nec
    0.43
    मस
    0.43
    ن
    0.42
    Books
    0.41
     Realtors
    0.40
     Guns
    0.39
    Touched
    0.39
     scratched
    0.39
    POSITIVE LOGITS
     libel
    0.53
     отказа
    0.50
     병
    0.48
     состав
    0.47
    เวอร์
    0.47
     тела
    0.46
     зем
    0.46
     เพิ่ม
    0.46
     испыта
    0.45
     колеба
    0.45
    Activations Density 0.003%

    No Known Activations