© 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. 45716
    Prev
    Next
    INDEX
    Explanations

    guidelines for entry

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

    gtk/widget calls

    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
     PAC
    0.44
     shortened
    0.43
     Phy
    0.40
     SMB
    0.40
     PAT
    0.39
     jad
    0.37
     NST
    0.37
    裳
    0.36
     Puerto
    0.36
     harmed
    0.36
    POSITIVE LOGITS
    🍗
    0.52
    ógł
    0.51
     দিয়েছেন
    0.50
    🕋
    0.50
    🕛
    0.50
    🍲
    0.48
    🍽
    0.48
     miei
    0.47
    🍴
    0.47
    뇰
    0.47
    Activations Density 0.000%

    No Known Activations