© 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. 83381
    Prev
    Next
    INDEX
    Explanations

    measure guide

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

    someone explain calculate array sample biomedical

    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
    i
    0.57
    t
    0.56
    ul
    0.55
    0
    0.51
     =
    0.50
     Sand
    0.50
    '
    0.49
     Machine
    0.49
     Co
    0.48
     GUI
    0.48
    POSITIVE LOGITS
    鉑
    0.57
    更好的
    0.55
    вати
    0.54
     ಪ್ರಮಾಣ
    0.53
    良好的
    0.53
    𝙍
    0.53
     있도록
    0.52
    נה
    0.51
     ದೊಡ್ಡ
    0.50
    ៤
    0.50
    Activations Density 0.000%

    No Known Activations