© 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. 142563
    Prev
    Next
    INDEX
    Explanations

    spudding Edition. proof is in the pudding though. bride and groom and their families

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

    concepts or lists associated

    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
    イナー
    0.44
     karbon
    0.43
    rú
    0.43
    ╥
    0.43
    avano
    0.43
    avl
    0.42
    iriya
    0.42
    mä
    0.42
    igens
    0.42
    pren
    0.42
    POSITIVE LOGITS
     campos
    0.45
    ຽ
    0.45
    িনীত
    0.44
    ు
    0.44
    যোগ্য
    0.43
     decorated
    0.42
     AGRICULTURAL
    0.42
    Prox
    0.42
    槙
    0.41
    ម្រ
    0.41
    Activations Density 0.000%

    No Known Activations