© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 209113
    Prev
    Next
    INDEX
    Explanations

    phrases starting with update

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

    negative 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
     물질
    0.59
    決して
    0.53
    тли
    0.52
    
    0.52
    า
    0.52
    촛
    0.52
    acchati
    0.51
     মৃত্যুদ
    0.51
    Probit
    0.51
     paljon
    0.50
    POSITIVE LOGITS
    server
    0.42
    **
    0.41
    '))
    0.40
     قبول
    0.40
    бору
    0.40
     زاده
    0.40
    s
    0.39
     Dispon
    0.39
    بح
    0.39
     गौर
    0.39
    Activations Density 0.000%

    No Known Activations