© 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. 187472
    Prev
    Next
    INDEX
    Explanations

    ticket, walked, businesses, games, residents

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

    . This

    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
    
    0.55
    ມ
    0.54
    σταν
    0.51
    προ
    0.50
    ૄ
    0.49
    ד
    0.49
    剿
    0.47
    
    0.47
    뷊
    0.46
    مد
    0.46
    POSITIVE LOGITS
    at
    0.49
    as
    0.48
    '
    0.48
    vas
    0.44
     பாத
    0.43
     Motiv
    0.43
    a
    0.43
     বিষয়
    0.43
    ness
    0.41
     साव
    0.41
    Activations Density 0.001%

    No Known Activations