© 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. 223446
    Prev
    Next
    INDEX
    Explanations

    after punctuation or article

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

    Open Neural Network Exchange

    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
    пление
    0.55
    ptăm
    0.50
     предложение
    0.49
     наше
    0.49
    బాబు
    0.49
    utico
    0.49
    ㄶ
    0.49
    τρι
    0.47
    우리
    0.47
    낫
    0.47
    POSITIVE LOGITS
     focuses
    0.49
     {
    0.45
     without
    0.45
     takes
    0.44
     C
    0.43
     containing
    0.43
     reflecting
    0.41
     जैसा
    0.41
     conducts
    0.40
    aard
    0.40
    Activations Density 0.005%

    No Known Activations