© 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. 182073
    Prev
    Next
    INDEX
    Explanations

    conjunctions, lists, or sequences

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

    romanized korean love phrases

    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
     Bradshaw
    0.46
     เหลือ
    0.41
     ;
    0.41
    iman
    0.40
     motive
    0.40
     lobster
    0.39
    мпа
    0.39
     we
    0.39
     deem
    0.39
    क्रम
    0.38
    POSITIVE LOGITS
     особы
    0.52
     নয়াদ
    0.51
    textColour
    0.49
    椪
    0.49
    𝗽
    0.49
    瑆
    0.48
    프
    0.48
    浅
    0.48
    тельные
    0.47
    ব্যা
    0.47
    Activations Density 0.001%

    No Known Activations