© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199126
    Prev
    Next
    INDEX
    Explanations

    common word sequences

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

    words indicating cause, reason, or subsequent state

    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
    Negative Logits
     అంటున్నారు
    0.47
     Rajapak
    0.46
     Albania
    0.45
     Margarita
    0.45
     necesarias
    0.44
     Kosovo
    0.44
    <0x80>
    0.42
     coba
    0.42
     nöt
    0.42
     tetragonal
    0.42
    POSITIVE LOGITS
    omitem
    0.49
    រយៈ
    0.48
    cipher
    0.47
    维
    0.45
    内置
    0.44
    殡
    0.44
    ORDERS
    0.44
    OFFSET
    0.43
    million
    0.43
    pson
    0.43
    Activations Density 0.000%

    No Known Activations