© 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. 143542
    Prev
    Next
    INDEX
    Explanations

    judge and transport

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

    non-english words, numbers, adverbs

    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
    sqlUpdate
    0.46
    参数向量
    0.46
    ल्ले
    0.45
    率为
    0.43
    simulation
    0.41
    物联网
    0.40
    픕
    0.40
    از
    0.40
    muted
    0.40
    jobSize
    0.40
    POSITIVE LOGITS
     wanneer
    0.53
     सकती
    0.49
     ketika
    0.49
     quando
    0.48
     terre
    0.47
    Cost
    0.47
     ramb
    0.46
    ֛
    0.46
     cuando
    0.46
     huis
    0.45
    Activations Density 0.000%

    No Known Activations