© 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. 208073
    Prev
    Next
    INDEX
    Explanations

    Business visits

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

    acrostic poems

    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
    THE
    0.52
    Dust
    0.52
    বের
    0.47
     razvoja
    0.47
    Residents
    0.47
    Development
    0.47
    মহ
    0.46
    윈
    0.46
     razvoj
    0.46
    Lost
    0.46
    POSITIVE LOGITS
    ன்த
    0.61
     関数
    0.55
     participle
    0.50
     よく
    0.48
     UCF
    0.48
     believer
    0.48
     juntos
    0.48
    ptuous
    0.47
     ล่ะ
    0.47
     constant
    0.46
    Activations Density 0.001%

    No Known Activations