© 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. 113545
    Prev
    Next
    INDEX
    Explanations

    various nouns

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

    domain, learning, code, service, systems

    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
    。
    0.73
    ।
    0.61
    AN
    0.60
    मा
    0.57
    да
    0.57
    ORE
    0.53
    या
    0.52
    نا
    0.52
    ED
    0.51
    IS
    0.50
    POSITIVE LOGITS
     Emeritus
    0.68
    ità
    0.63
     ór
    0.62
     Highness
    0.62
     sooo
    0.62
     soooo
    0.61
     tão
    0.57
    ţ
    0.57
    ỹ
    0.57
    țin
    0.57
    Activations Density 0.945%

    No Known Activations