© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 181272
    Prev
    Next
    INDEX
    Explanations

    specific locations and things

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

    complex numbers and challenging objectives

    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
    য়াছে
    0.54
    BagConstraints
    0.52
    ப்பட்டுள்ளது
    0.51
    䀖
    0.49
     परेश
    0.48
    侎
    0.47
     دارند
    0.47
    पोरेशन
    0.46
    ཱ
    0.46
    êté
    0.46
    POSITIVE LOGITS
    n
    0.54
    are
    0.49
     on
    0.49
    l
    0.49
    of
    0.49
    code
    0.49
     to
    0.48
    h
    0.47
    axis
    0.47
     auf
    0.46
    Activations Density 0.001%

    No Known Activations