© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56969
    Prev
    Next
    INDEX
    Explanations

    code comments and imports

    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
    🈚
    0.41
    🥡
    0.39
    ẵ
    0.38
    टने
    0.38
     ನೀರಿನ
    0.36
    }${
    0.36
    batt
    0.36
    ayet
    0.36
    ەی
    0.35
    гляд
    0.35
    POSITIVE LOGITS
     liten
    0.42
     fear
    0.40
     Destroy
    0.40
    此
    0.40
     naive
    0.39
     calling
    0.39
     Rovio
    0.39
     advantage
    0.38
     destroy
    0.38
     Eks
    0.37
    Activations Density 0.002%

    No Known Activations