Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64970
    Prev
    Next
    INDEX
    Explanations

    melt, town, anxiety, track, snowflakes

    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
    s
    0.66
    slate
    0.54
    commitment
    0.51
    だろう
    0.51
     commitment
    0.49
    t
    0.48
     dedication
    0.47
    n
    0.47
    mi
    0.45
    sponsored
    0.45
    POSITIVE LOGITS
    皤
    0.55
    姮
    0.54
    秫
    0.50
     වෙත
    0.50
    硬盘
    0.47
    렙
    0.47
     سفید
    0.47
    棌
    0.46
     విధాన
    0.46
    磁盘
    0.46
    Activations Density 0.007%

    No Known Activations