© 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. 11215
    Prev
    Next
    INDEX
    Explanations

    spiders

    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
    I
    0.44
    \
    0.41
     que
    0.41
     Penguin
    0.39
    urie
    0.38
     Ethics
    0.38
     Mod
    0.38
     PNG
    0.38
     jedem
    0.38
    Hor
    0.37
    POSITIVE LOGITS
     نحل
    0.41
     與
    0.38
     hyd
    0.38
     scrollBody
    0.38
    robe
    0.36
    專家
    0.35
     ৪
    0.35
     ncol
    0.35
     hydrology
    0.35
    ུ་
    0.35
    Activations Density 0.005%

    No Known Activations