© 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. 24896
    Prev
    Next
    INDEX
    Explanations

    technical terms and brands

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

    always, only, always

    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
    퀼
    0.44
     包括
    0.41
     পাইনি
    0.41
     উদযাপন
    0.40
    BUR
    0.40
    ରି
    0.39
    包括
    0.39
    它们的
    0.39
    burst
    0.38
    Greeting
    0.38
    POSITIVE LOGITS
    ،
    0.61
     همیشه
    0.48
     ،
    0.45
     sürekli
    0.45
     هیچ
    0.44
     você
    0.44
     only
    0.43
    ，
    0.43
     always
    0.42
     Only
    0.42
    Activations Density 0.000%

    No Known Activations