© 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. 197429
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or conjunctions

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

    number, Conservatvies, managing, bottles, updated

    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
     విధంగా
    0.48
     Dương
    0.45
    ＋
    0.45
     있는데요
    0.45
     addNew
    0.45
    ；
    0.44
     Sht
    0.44
     Eğer
    0.43
    一
    0.43
    䀦
    0.43
    POSITIVE LOGITS
     carbs
    0.52
     शुक्ल
    0.49
     tử
    0.47
    ຖື
    0.47
     público
    0.45
    elerde
    0.44
    молу
    0.44
    ায়া
    0.44
     مید
    0.44
     ou
    0.43
    Activations Density 0.000%

    No Known Activations