© 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. 22326
    Prev
    Next
    INDEX
    Explanations

    postcode followed by letters

    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
    u
    0.50
    verse
    0.48
    ne
    0.48
    te
    0.47
    ní
    0.46
    迅速
    0.46
     retrospect
    0.45
    ioxid
    0.45
    quick
    0.45
     сопротив
    0.45
    POSITIVE LOGITS
    КУ
    0.46
     apothecary
    0.46
     enumeration
    0.46
     departures
    0.44
    ：
    0.44
     espaces
    0.43
     acronym
    0.43
     terrazzo
    0.43
     목록
    0.43
    站点
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.