© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20745
    Prev
    Next
    INDEX
    Explanations

    frequency of occurrence

    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_16_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
    :
    0.90
    in
    0.81
    <0x0D>
    0.74
    {
    0.72
    م
    0.72
    ations
    0.68
    ન
    0.66
    \
    0.66
     la
    0.65
     une
    0.65
    POSITIVE LOGITS
     frequency
    1.16
    Frequency
    1.05
    frequency
    1.03
     Frequency
    1.00
     fréquence
    0.99
    频率
    0.95
    FREQUENCY
    0.93
    频
    0.90
     frequência
    0.88
    freq
    0.87
    Activations Density 0.043%

    No Known Activations