© 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. 251883
    Prev
    Next
    INDEX
    Explanations

    committed adultery, clear coat, told reporters

    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
    *
    0.46
     compartmental
    0.44
    achute
    0.44
     offseason
    0.44
     或者
    0.43
     acreage
    0.42
     餐
    0.42
     अमाउंट
    0.41
    hitung
    0.41
     estimated
    0.41
    POSITIVE LOGITS
    Чер
    0.48
     γλώ
    0.48
    리기
    0.46
     ANOTHER
    0.45
    얘
    0.45
    駱
    0.45
    的模型
    0.44
     பலர்
    0.44
    🇼
    0.44
     jeudi
    0.44
    Activations Density 0.001%

    No Known Activations