© 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. 120397
    Prev
    Next
    INDEX
    Explanations

    conserving surgery, sees as, surviving life

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

    after first

    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
    ashire
    0.51
    انه
    0.48
    都已经
    0.48
    寰
    0.47
     শিল্পী
    0.46
    씽
    0.46
    لاق
    0.44
    انات
    0.44
    ولا
    0.44
    法人
    0.43
    POSITIVE LOGITS
     otor
    0.48
    >`;
    0.46
     defined
    0.43
    唵
    0.43
     incr
    0.42
     धम
    0.42
    oin
    0.41
     allyl
    0.41
     उपस्थिति
    0.41
     presence
    0.41
    Activations Density 0.002%

    No Known Activations