© 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. 120713
    Prev
    Next
    INDEX
    Explanations

    first iterations of

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

    stools, ease, contributed

    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
     እድ
    0.49
    艰
    0.48
    爵
    0.48
    জ্জিত
    0.48
    𐰣
    0.47
    告诉我
    0.46
    ᵚ
    0.46
    工具
    0.45
    Stacks
    0.45
     বসু
    0.45
    POSITIVE LOGITS
    0.57
     insured
    0.56
    \
    0.52
     el
    0.52
    ă
    0.51
     \
    0.48
     kidneys
    0.47
    а
    0.47
     an
    0.46
     kidney
    0.46
    Activations Density 0.000%

    No Known Activations