© 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. 185001
    Prev
    Next
    INDEX
    Explanations

    attempt getting

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

    interest to, integer larger, sought after

    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
    Not in Any Lists

    No Comments

    Negative Logits
     古
    0.46
    I
    0.45
     花
    0.45
    iko
    0.44
     تھ
    0.44
    imin
    0.44
    iman
    0.43
    地形
    0.43
    oten
    0.43
    öp
    0.42
    POSITIVE LOGITS
     sonrisa
    0.49
     başlayan
    0.46
     শিবির
    0.43
     obecnie
    0.43
     sorriso
    0.42
     orgullo
    0.41
    ﹁
    0.41
     серде
    0.41
     przyst
    0.41
    Trimethyl
    0.41
    Activations Density 0.000%

    No Known Activations