© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160632
    Prev
    Next
    INDEX
    Explanations

    gift ideas

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

    ilot horizon descent

    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
     canisters
    0.47
     engagements
    0.46
     فاس
    0.46
    넣
    0.46
    sbParams
    0.45
     예를
    0.45
    のうち
    0.45
    ೊಳ್ಳ
    0.45
    껄
    0.44
    這樣的
    0.44
    POSITIVE LOGITS
    (
    0.43
    สัม
    0.42
     bak
    0.41
    െന്ന
    0.41
    มิ
    0.41
    ilot
    0.41
     seç
    0.41
    రించ
    0.41
    ชั้น
    0.41
     terakhir
    0.40
    Activations Density 0.001%

    No Known Activations