© 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. 40-GEMMASCOPE-2-RES-262K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis signals code block

    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_40_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
    细菌
    0.33
    쇠
    0.33
    ෙස
    0.32
     PHYSI
    0.32
    Crown
    0.31
    Neck
    0.31
     कशी
    0.31
     водой
    0.31
    絲
    0.31
    スパ
    0.31
    POSITIVE LOGITS
     {
    0.60
     {//
    0.51
     thì
    0.45
    则
    0.38
     فإن
    0.37
    else
    0.36
                
    0.36
     maka
    0.35
     则
    0.35
    {
    0.35
    Activations Density 0.045%

    No Known Activations