© 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. 66853
    Prev
    Next
    INDEX
    Explanations

    special wordswine making detailsgeography termstesting processesround objects

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

    paradoxical logic and datasets

    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
    打造
    0.52
    ുട
    0.43
     takım
    0.43
     souhaite
    0.43
    ຜ
    0.43
     feeble
    0.42
    प्‍
    0.42
    ＆
    0.42
    ہری
    0.40
    提交
    0.40
    POSITIVE LOGITS
     ছিলেন
    0.50
    adeh
    0.48
    었습니다
    0.46
    were
    0.44
     worsens
    0.44
     بودند
    0.43
     প্রেমের
    0.43
    သေး
    0.43
     ছিল
    0.42
    chow
    0.42
    Activations Density 0.002%

    No Known Activations