© 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. 208785
    Prev
    Next
    INDEX
    Explanations

    sports, names, numbers, and actions

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

    arguing or believing statements

    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
    ש
    0.50
    袠
    0.50
    জনক
    0.49
     Phrase
    0.48
     ع
    0.47
     Boyce
    0.46
     etwas
    0.45
     Twelve
    0.45
     Surve
    0.45
     Sexual
    0.44
    POSITIVE LOGITS
    ό
    0.47
     фонбет
    0.45
    defendant
    0.43
     fanatics
    0.43
     नती
    0.42
    ībā
    0.40
    螳
    0.40
    ība
    0.39
     называется
    0.39
    không
    0.39
    Activations Density 0.002%

    No Known Activations