© 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. 84498
    Prev
    Next
    INDEX
    Explanations

    for the

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

    Innovation and collaboration

    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
     จังหวัด
    0.54
     เขา
    0.52
     میچ
    0.52
     กล่าว
    0.51
    Beverungen
    0.50
     ดาว
    0.50
     剤
    0.50
     ท่าน
    0.50
    जीत
    0.49
    เขา
    0.49
    POSITIVE LOGITS
    0.51
    1
    0.49
    ac
    0.46
    qu
    0.45
     бюро
    0.45
     callBack
    0.43
     two
    0.42
     receber
    0.42
    di
    0.41
     registers
    0.41
    Activations Density 0.000%

    No Known Activations