© 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. 152225
    Prev
    Next
    INDEX
    Explanations

    specific phrases and words

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

    Concentrate, noticed, take, same, Python, API, Investing

    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
    薢
    0.52
     Worksheet
    0.51
    дцать
    0.45
     그런데
    0.45
    чною
    0.45
    伲
    0.45
     Pleasant
    0.43
     Grub
    0.43
     Micah
    0.43
    䈤
    0.43
    POSITIVE LOGITS
    which
    0.49
    Ku
    0.46
    that
    0.45
    expansion
    0.45
    is
    0.45
    in
    0.44
    restart
    0.44
    inse
    0.43
    ku
    0.43
    imagen
    0.43
    Activations Density 0.003%

    No Known Activations