© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194544
    Prev
    Next
    INDEX
    Explanations

    relies on

    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
     }}$.
    0.41
    鐘
    0.39
     }{
    0.39
     Marty
    0.39
    }}$
    0.38
     lib
    0.38
     Naam
    0.38
    बह
    0.36
    onden
    0.36
    lib
    0.36
    POSITIVE LOGITS
     representation
    0.46
    につなが
    0.40
     사용자
    0.40
     روبل
    0.38
     技術
    0.36
     उपयोगकर्ता
    0.36
    ื่ม
    0.36
    engkapi
    0.36
    𝒉
    0.36
    ệc
    0.36
    Activations Density 0.006%

    No Known Activations