© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110932
    Prev
    Next
    INDEX
    Explanations

    numbers in the thousands

    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
    znej
    0.43
     ті
    0.39
     рі
    0.39
    achtree
    0.38
    ல்லாம்
    0.38
    承
    0.38
    ohu
    0.37
     Fahrenheit
    0.36
    unek
    0.36
    ToShow
    0.36
    POSITIVE LOGITS
    ০০০
    0.50
     тысяч
    0.50
     هزار
    0.48
     হাজারের
    0.46
     ஆயிர
    0.43
     हज़ार
    0.42
     हजार
    0.42
    thousand
    0.40
    xxx
    0.40
    ٬
    0.39
    Activations Density 0.039%

    No Known Activations