© 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. 197392
    Prev
    Next
    INDEX
    Explanations

    seekers or information requests

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

    finding specific arguments or items

    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
     ফিল্ম
    0.50
     ներ
    0.48
    利
    0.47
    托管
    0.46
     ရက်
    0.46
     文化
    0.45
    兆
    0.45
    风险
    0.45
     程序
    0.45
    器件
    0.44
    POSITIVE LOGITS
     Rani
    0.59
    Heute
    0.51
     Nure
    0.49
     Fuji
    0.49
    Pupp
    0.48
    USED
    0.47
     deix
    0.47
     apud
    0.47
    În
    0.46
     Belinda
    0.46
    Activations Density 0.001%

    No Known Activations