© 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. 158113
    Prev
    Next
    INDEX
    Explanations

    later, simply, approve

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

    specific phrases and technical terms

    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
    じた
    0.49
    絓
    0.47
    ोजा
    0.46
    rad
    0.45
    ยาง
    0.45
    t
    0.45
    險
    0.45
    numerator
    0.44
    inez
    0.43
    ז
    0.43
    POSITIVE LOGITS
     transitory
    0.51
     transitioned
    0.49
    цької
    0.48
     Verbind
    0.48
    utional
    0.45
     Demand
    0.45
     prudent
    0.45
     retourner
    0.44
     transduction
    0.44
     Spokes
    0.44
    Activations Density 0.001%

    No Known Activations