© 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. 196026
    Prev
    Next
    INDEX
    Explanations

    we like to CI

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

    explaining specific concepts or details

    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
    佐
    0.48
    梅
    0.46
    SENT
    0.44
    造
    0.44
     méthodique
    0.43
     佐
    0.42
    전자
    0.42
    保
    0.42
    単
    0.41
    NETT
    0.41
    POSITIVE LOGITS
     ఒప్ప
    0.54
    رق
    0.49
     همین
    0.48
     ఏద
    0.46
     বিশেষজ্ঞ
    0.46
     विशेषज्ञों
    0.46
     diabetics
    0.45
    ToDo
    0.45
     গানের
    0.45
     सुपरहिट
    0.45
    Activations Density 0.001%

    No Known Activations