© 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. 65149
    Prev
    Next
    INDEX
    Explanations

    next ongoing PURCH might practical chronic Emerging Unique

    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
     Poker
    0.44
     Tem
    0.41
    j
    0.40
     Plat
    0.39
    oline
    0.39
    elun
    0.38
    el
    0.38
     tem
    0.38
    <0xBB>
    0.37
    apabb
    0.37
    POSITIVE LOGITS
     со
    0.40
     규모
    0.40
    忥
    0.38
     авиа
    0.38
    PPTV
    0.38
    的大小
    0.37
     코로나
    0.37
    OF
    0.37
     เฮ
    0.37
    也能
    0.36
    Activations Density 0.006%

    No Known Activations