© 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. 94361
    Prev
    Next
    INDEX
    Explanations

    phones, death, justice, clearly

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

    explains function and purpose

    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
    حث
    0.46
    सेस
    0.44
    成就
    0.43
    ल्लाला
    0.43
    call
    0.41
     ú
    0.41
    ת
    0.41
    鉻
    0.41
     لت
    0.41
     android
    0.41
    POSITIVE LOGITS
     выбрали
    0.46
     mattered
    0.46
     основним
    0.46
    columnwidth
    0.46
     Meadow
    0.45
     ήταν
    0.45
     Mildred
    0.44
    élément
    0.43
    Wilson
    0.42
     ખૂબ
    0.42
    Activations Density 0.001%

    No Known Activations