© 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. 21672
    Prev
    Next
    INDEX
    Explanations

    corporate data

    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
    一つの
    0.48
    いくつかの
    0.45
    একটা
    0.44
     kwamba
    0.42
    ᾧ
    0.41
    regierung
    0.41
     অভিনন্দন
    0.41
    也許
    0.41
     OBJECTTYPE
    0.40
    াদা
    0.40
    POSITIVE LOGITS
    ِی
    0.44
    的学习
    0.42
     profondes
    0.42
     Nowak
    0.41
     learners
    0.40
    ில்
    0.39
    专业
    0.39
    .</
    0.39
     öğrenciler
    0.39
    .}
    0.38
    Activations Density 0.000%

    No Known Activations