© 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. 219218
    Prev
    Next
    INDEX
    Explanations

    processes, services, and agreements

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

    future strategy and outcomes

    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
     gọi
    0.49
    :')
    0.48
    ,$$
    0.48
     pyr
    0.47
     '}
    0.46
    gr
    0.45
     格
    0.45
     dx
    0.45
     Hochzeit
    0.45
     worshipped
    0.45
    POSITIVE LOGITS
    ਲ
    0.59
    ่น
    0.52
    ਦਰ
    0.49
    いくつ
    0.49
    ਦੇ
    0.48
    ﻮ
    0.48
    煕
    0.46
    ਦੀ
    0.46
    ս
    0.46
    บรร
    0.46
    Activations Density 0.000%

    No Known Activations