© 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. 183133
    Prev
    Next
    INDEX
    Explanations

    credit cards and release

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

    using ingredients

    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
     Kenn
    0.45
     kö
    0.43
     KEN
    0.42
    LocalDateTime
    0.42
    c
    0.42
    нт
    0.41
     ktoré
    0.41
     hém
    0.40
     ken
    0.40
    Kenn
    0.40
    POSITIVE LOGITS
    کار
    0.51
     punctuated
    0.49
    ツアー
    0.48
    গীর
    0.48
    ponge
    0.47
    २०
    0.47
    喳
    0.47
     روپے
    0.47
    ிரஸ்
    0.46
     ایجاد
    0.46
    Activations Density 0.001%

    No Known Activations