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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12249
    Prev
    Next
    INDEX
    Explanations

    frequency of occurrences

    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_40_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
    MnO
    0.38
     धारण
    0.37
    DeferredGroup
    0.37
     തിര
    0.37
    ំព
    0.35
    オ
    0.35
    phans
    0.35
    codiles
    0.35
    --’
    0.35
     ignored
    0.34
    POSITIVE LOGITS
     frequency
    1.34
     Frequency
    1.27
    Frequency
    1.16
    frequency
    1.14
     fréquence
    1.11
     frequ
    1.07
    频率
    1.02
    頻
    1.02
     freq
    1.01
     frecuencia
    1.00
    Activations Density 0.007%

    No Known Activations