© 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. 116302
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    relationship, barrier, test, pick, Evans

    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
     Chat
    0.53
     of
    0.51
     is
    0.51
     or
    0.50
     ChatGPT
    0.50
    ;
    0.49
     Holi
    0.49
     Have
    0.49
     YouTuber
    0.48
     adjective
    0.48
    POSITIVE LOGITS
    hältnis
    0.54
    İŞ
    0.54
     мира
    0.52
    岦
    0.52
    asını
    0.51
     sürekli
    0.51
    Databaze
    0.50
    سین
    0.50
     uygulama
    0.49
    itäten
    0.49
    Activations Density 0.001%

    No Known Activations