© 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. 160382
    Prev
    Next
    INDEX
    Explanations

    Texas, year, law, entrance

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

    for survival

    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
     کہ
    0.49
    animated
    0.47
    移動
    0.46
     移動
    0.46
    cepat
    0.45
    kta
    0.45
     ከ
    0.44
     ی
    0.44
     ι
    0.43
    estay
    0.43
    POSITIVE LOGITS
     Case
    0.50
     CASE
    0.46
    璜
    0.46
    挑选
    0.45
     Selection
    0.44
     Protecting
    0.44
    回头
    0.43
     Sea
    0.43
    CASE
    0.42
    肅
    0.42
    Activations Density 0.001%

    No Known Activations