© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    plumbing and tiling

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

    materials and programming constructs

    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
     guest
    0.42
    ക്ക്‌
    0.42
    query
    0.41
    ﻭ
    0.39
    ﻪ
    0.39
     costru
    0.39
    参考
    0.39
     recirculation
    0.38
    と思いますが
    0.38
     수
    0.38
    POSITIVE LOGITS
    Pclass
    0.54
     sermons
    0.52
    rafpunkte
    0.51
     comedies
    0.50
     insides
    0.50
    ractor
    0.49
     gutters
    0.49
    Comedy
    0.49
     डिफरेंट
    0.49
    ssia
    0.49
    Activations Density 0.000%

    No Known Activations