© 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. 206434
    Prev
    Next
    INDEX
    Explanations

    just, too, wanted, conditions, time, blowing

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

    research question

    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
    akoti
    0.61
    "
    0.44
    ੁੱ
    0.41
    acquisto
    0.41
    बद्दल
    0.41
     uptick
    0.41
     Blumen
    0.41
     taglio
    0.40
    ampuan
    0.39
    stopping
    0.39
    POSITIVE LOGITS
     ইউনিভার্সি
    0.48
     entertained
    0.46
    𝑑
    0.46
    json
    0.45
    ructures
    0.45
     espec
    0.45
     wants
    0.45
    onaut
    0.45
    dV
    0.45
     intends
    0.44
    Activations Density 0.000%

    No Known Activations