© 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. 74484
    Prev
    Next
    INDEX
    Explanations

    verb and preposition pairs

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

    validating cloud applications

    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
    ‌
    0.53
     ડિ
    0.52
     Daylight
    0.46
    Ē
    0.46
     DIST
    0.45
    ‌‌
    0.43
    干扰
    0.43
     जान
    0.42
     округу
    0.42
    া
    0.42
    POSITIVE LOGITS
     allocating
    0.55
     allocated
    0.47
    walle
    0.47
     allocations
    0.46
     crawling
    0.45
     emptying
    0.45
     ptr
    0.45
     railings
    0.43
     eigenvectors
    0.43
     affording
    0.43
    Activations Density 0.000%

    No Known Activations