© 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. 128348
    Prev
    Next
    INDEX
    Explanations

    main reason

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

    identifying key elements

    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
    Netflix
    0.44
    this
    0.43
    กระ
    0.42
    ע
    0.42
    ع
    0.41
     thông
    0.40
     villa
    0.40
     избран
    0.39
     DDoS
    0.38
    i
    0.38
    POSITIVE LOGITS
     glavni
    0.51
     resistant
    0.44
    Ⅹ
    0.44
     ejac
    0.43
     Hlav
    0.42
     huvud
    0.42
     ټ
    0.42
    বার্ট
    0.42
     wcout
    0.41
    ੯
    0.41
    Activations Density 0.002%

    No Known Activations