© 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. 44603
    Prev
    Next
    INDEX
    Explanations

    reporting or labeling text

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

    RNN, class, counts, life cycle

    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
    အတွ
    0.48
    受欢迎
    0.47
     त्यात
    0.47
     देण्यात
    0.46
    tag
    0.46
    ton
    0.45
    推送
    0.45
    형
    0.45
    倰
    0.44
     Steffen
    0.43
    POSITIVE LOGITS
     traverses
    0.49
     SERIAL
    0.46
     sepatu
    0.45
     маник
    0.45
     এমনকি
    0.45
     CYAN
    0.44
     designates
    0.44
     sentences
    0.43
    ।”
    0.43
     menggambarkan
    0.43
    Activations Density 0.000%

    No Known Activations