© 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. 10898
    Prev
    Next
    INDEX
    Explanations

    slightly

    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
    ן
    0.80
    ية
    0.68
     اربعه
    0.65
    人
    0.64
     الدین
    0.62
    কে
    0.59
    ской
    0.59
    ρα
    0.59
     Kapitel
    0.59
    kowej
    0.59
    POSITIVE LOGITS
    en
    0.70
    y
    0.70
    ти
    0.59
    uh
    0.55
    K
    0.55
    к
    0.54
     modify
    0.54
    S
    0.54
    ا
    0.53
    asn
    0.52
    Activations Density 0.034%

    No Known Activations