© 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. 128741
    Prev
    Next
    INDEX
    Explanations

    numbers or digits

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

    numbers and durations

    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
    oth
    0.49
    utt
    0.47
    curs
    0.47
    (
    0.46
    nite
    0.46
     निवार
    0.46
    graphs
    0.46
    ials
    0.45
    ysts
    0.45
     endpoints
    0.45
    POSITIVE LOGITS
     six
    0.57
     छह
    0.53
     nine
    0.49
     four
    0.49
    с
    0.48
     fifteen
    0.48
     sechs
    0.47
    正面
    0.47
    六
    0.46
    س
    0.46
    Activations Density 0.001%

    No Known Activations