© 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. 91085
    Prev
    Next
    INDEX
    Explanations

    client name

    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
    ewnątrz
    0.46
    Animals
    0.44
    alist
    0.42
    ikation
    0.42
    乐趣
    0.41
    Being
    0.40
    句话
    0.39
    ㄧ
    0.39
    泻
    0.39
     setDescription
    0.39
    POSITIVE LOGITS
     комби
    0.50
     tau
    0.48
     bukti
    0.47
     lagi
    0.45
     tuber
    0.43
     shingles
    0.42
    よいよ
    0.42
     tapi
    0.41
     kuliah
    0.41
     ši
    0.41
    Activations Density 0.000%

    No Known Activations