© 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. 29464
    Prev
    Next
    INDEX
    Explanations

    common adjective phrases

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

    listing/defining key points

    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
    ন
    0.54
     ae
    0.49
     '../../
    0.48
     AE
    0.46
    ン
    0.46
    デ
    0.46
    入力
    0.45
    ル
    0.45
    இந்த
    0.45
     photosynthesis
    0.45
    POSITIVE LOGITS
     préciser
    0.50
     unenforceable
    0.45
     أع
    0.45
    aminan
    0.44
    पुढे
    0.44
     ännu
    0.44
     أصبح
    0.44
     ஏற்றுக்கொள்ள
    0.44
     Kessler
    0.44
     considérer
    0.44
    Activations Density 0.000%

    No Known Activations