© 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. 208237
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases, numbers, or conjunctions

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

    Formatting, smartphones, specific names

    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
     einen
    0.49
    Tere
    0.48
     einem
    0.45
    鏟
    0.42
     whatsoever
    0.41
     Ehr
    0.40
     uop
    0.40
     Tere
    0.39
     amateurs
    0.39
     upland
    0.39
    POSITIVE LOGITS
     मतगणना
    0.49
     रैली
    0.46
     সুল
    0.46
     ರೀತಿ
    0.46
     슈
    0.45
    ទី
    0.45
    éclair
    0.44
    鸫
    0.44
     दावे
    0.44
     şekilde
    0.44
    Activations Density 0.001%

    No Known Activations