© 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. 195002
    Prev
    Next
    INDEX
    Explanations

    basket

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

    enough times

    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
    尿
    0.49
     پی
    0.46
     Urine
    0.43
    álisis
    0.42
     в
    0.41
     gastric
    0.40
     İş
    0.40
     периоди
    0.40
     reportedly
    0.40
     ఓ
    0.40
    POSITIVE LOGITS
    瑄
    0.48
    LEGO
    0.45
    \\.
    0.45
     রকমের
    0.44
    dialog
    0.44
    IVERSITY
    0.44
    他們的
    0.44
    uptools
    0.42
     অথবা
    0.41
    Uy
    0.41
    Activations Density 0.000%

    No Known Activations