© 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. 196288
    Prev
    Next
    INDEX
    Explanations

    no ... him

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

    detailed brief for a court

    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
    虜
    0.48
    RESEARCH
    0.47
     استف
    0.46
    琿
    0.46
     Pengembangan
    0.46
    THE
    0.45
    োগ্রাফ
    0.45
     عصر
    0.45
    ব্যাপী
    0.45
    PRODUCTS
    0.45
    POSITIVE LOGITS
     decimals
    0.44
    :
    0.42
    设定
    0.42
     fileSize
    0.42
    νη
    0.41
    OutputFile
    0.41
    ↵
    0.40
     fare
    0.40
     chord
    0.40
     {(
    0.40
    Activations Density 0.001%

    No Known Activations