© 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. 8803
    Prev
    Next
    INDEX
    Explanations

    Macro routine, collider suspension, matrix calculation

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

    python, javascript, and jquery

    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
     다음과
    0.45
     you
    0.44
    咱们
    0.44
    你可以
    0.43
    ที่คุณ
    0.43
    如下
    0.42
     this
    0.40
    :\\
    0.40
     নিম্নলিখিত
    0.40
     следующее
    0.39
    POSITIVE LOGITS
     너무
    0.44
     disturbs
    0.43
     misconceptions
    0.40
     nessuno
    0.40
    曖
    0.40
     Diarsipkan
    0.39
     keine
    0.39
     misunder
    0.39
     Archivado
    0.39
    Jähr
    0.38
    Activations Density 0.007%

    No Known Activations