© 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. 27712
    Prev
    Next
    INDEX
    Explanations

    algorithms, statistics, and specific terms

    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
    endimento
    0.41
    الحمد
    0.39
     Mad
    0.38
     $\%$
    0.37
    ifies
    0.36
    amins
    0.36
    ermos
    0.36
    rait
    0.36
     gained
    0.36
    chievement
    0.36
    POSITIVE LOGITS
    冗
    0.50
     ఉండ
    0.44
    萤
    0.42
     mạng
    0.41
    虚拟机
    0.41
     શક
    0.40
     пассажи
    0.40
     ইংরেজ
    0.40
     оптими
    0.40
    员
    0.40
    Activations Density 0.001%

    No Known Activations