© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186704
    Prev
    Next
    INDEX
    Explanations

    promotes, free, numbers, within

    np_acts-logits-general · gemini-2.5-flash-lite

    examples and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     macar
    0.54
     piè
    0.48
    ίν
    0.48
    လည်း
    0.46
     جائزے
    0.46
     dout
    0.46
    ctx
    0.45
    楂
    0.45
    низ
    0.44
     S
    0.43
    POSITIVE LOGITS
    esempio
    0.52
     एग्जांपल
    0.48
     интенсив
    0.45
     mucho
    0.44
     advances
    0.44
     ভবিষ্য
    0.43
    fections
    0.42
     इलेक्ट्रॉनिक
    0.42
     exemplo
    0.41
    cer
    0.41
    Activations Density 0.000%

    No Known Activations