© 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. 19097
    Prev
    Next
    INDEX
    Explanations

    non-english characters and words

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

    detailed explanation or breakdown

    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
    旁
    0.50
    每天
    0.48
    提到
    0.45
     thí
    0.45
     ভারপ্রাপ্ত
    0.44
    <0x80>
    0.44
     সভাপতিত্ব
    0.44
     notebook
    0.43
     dictates
    0.42
     cellphone
    0.42
    POSITIVE LOGITS
    UTR
    0.53
    🗽
    0.50
    acją
    0.49
     ܐ
    0.49
    บู
    0.49
    ONY
    0.47
     analisi
    0.47
    COVERY
    0.46
    CLUSTER
    0.46
    Мі
    0.46
    Activations Density 0.000%

    No Known Activations