© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    autoit or phpbb scripts

    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
     buyers
    0.50
     Buyers
    0.46
     buyer
    0.44
     Subscribers
    0.42
    클
    0.41
     матч
    0.41
    ോള
    0.41
     Buyer
    0.40
     Sellers
    0.40
    답
    0.40
    POSITIVE LOGITS
    Options
    0.41
    后面的
    0.40
    <sub>
    0.39
    <sup>
    0.39
    Contrast
    0.39
     гости
    0.39
    Hora
    0.38
    För
    0.37
    Axes
    0.37
    Display
    0.37
    Activations Density 0.010%

    No Known Activations