© 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. 113917
    Prev
    Next
    INDEX
    Explanations

    all risks, costs, and responsibility

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

    accepting risk

    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
    view
    0.45
    ivasena
    0.43
     spared
    0.42
    ⁸
    0.42
    いろんな
    0.42
    ୍କ
    0.41
     معاہد
    0.41
    qk
    0.40
     میرے
    0.40
    beam
    0.39
    POSITIVE LOGITS
    Informe
    0.47
    Gorgeous
    0.43
    Aplic
    0.43
    𝘤
    0.42
    acio
    0.41
     bathtub
    0.41
    렉
    0.41
    施工
    0.41
    Hace
    0.41
    构造
    0.40
    Activations Density 0.002%

    No Known Activations