© 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. 164462
    Prev
    Next
    INDEX
    Explanations

    assessment, jail, corrupted, exams

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

    explaining concepts or definitions

    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
    ))^{
    0.46
    istance
    0.43
    gage
    0.42
     भाग्य
    0.41
     GUARD
    0.41
    Sx
    0.40
    FieldValue
    0.40
     ১৩
    0.39
     도로
    0.38
     फिटनेस
    0.38
    POSITIVE LOGITS
    ва
    0.57
    an
    0.56
     Ribbon
    0.48
     Feynman
    0.47
    ᐋ
    0.46
     disen
    0.45
    த்தான்
    0.45
     ribbon
    0.45
    缠
    0.44
     Shik
    0.44
    Activations Density 0.003%

    No Known Activations