© 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. 2688
    Prev
    Next
    INDEX
    Explanations

    sometimes, often, usually

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

    sometimes, often, but

    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
    镙
    0.44
     Presently
    0.42
     forthwith
    0.41
     terrestre
    0.41
     mittels
    0.40
     ৭
    0.40
     সকলের
    0.39
    ４
    0.39
     상당히
    0.39
     उपरोक्त
    0.39
    POSITIVE LOGITS
     sometimes
    0.54
     Sometimes
    0.54
    往往
    0.53
    Sometimes
    0.51
     parfois
    0.50
     často
    0.50
     usually
    0.49
     often
    0.48
     nonprofits
    0.46
     obicei
    0.46
    Activations Density 0.062%

    No Known Activations