© 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. 188972
    Prev
    Next
    INDEX
    Explanations

    activities and events

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

    phrases with colon elaboration

    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
     Porta
    0.54
    José
    0.51
    Архі
    0.50
    포
    0.50
    Під
    0.47
    Посилання
    0.47
    Anche
    0.47
    Ｕ
    0.47
    Hiện
    0.46
    কবি
    0.45
    POSITIVE LOGITS
    af
    0.55
    argument
    0.54
    ana
    0.51
     diambil
    0.50
    <0x80>
    0.50
    aw
    0.48
    arg
    0.47
    integer
    0.47
     CEOs
    0.47
     năng
    0.46
    Activations Density 0.000%

    No Known Activations