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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133034
    Prev
    Next
    INDEX
    Explanations

    planning modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     акчага
    0.44
    ugg
    0.41
    insurance
    0.40
     일단
    0.39
     Siemens
    0.39
    鍑
    0.39
    dout
    0.38
     Pigeon
    0.37
     उक्त
    0.37
     entweder
    0.37
    POSITIVE LOGITS
     commutes
    0.36
    <0x19>
    0.35
     dives
    0.34
    ⒋
    0.34
     ול
    0.34
    סה
    0.34
    实例
    0.33
     leva
    0.33
     વરસ
    0.33
     días
    0.33
    Activations Density 0.000%

    No Known Activations