© 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. 157041
    Prev
    Next
    INDEX
    Explanations

    specialized technical terms

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

    foreign languages

    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
     prognosis
    0.46
    との
    0.46
    が
    0.46
    やはり
    0.45
    を追加
    0.45
     still
    0.45
    ০
    0.45
     Legislative
    0.44
    <0x80>
    0.44
    やっぱり
    0.44
    POSITIVE LOGITS
     पाणी
    0.54
    stech
    0.54
     бабу
    0.50
    terna
    0.50
     ekonomi
    0.49
     경제
    0.49
     barato
    0.48
     veřej
    0.48
     abitanti
    0.48
    кономи
    0.47
    Activations Density 0.001%

    No Known Activations