© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214080
    Prev
    Next
    INDEX
    Explanations

    questions, options

    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
     encapsulated
    0.44
     krom
    0.43
     McC
    0.39
    አ
    0.38
     crammed
    0.38
     meny
    0.38
    テッド
    0.37
     چنان
    0.36
     CNBC
    0.36
     kerap
    0.36
    POSITIVE LOGITS
     일반
    0.41
     vẫn
    0.41
     普通
    0.40
     αυτή
    0.40
     أيضًا
    0.40
    也在
    0.40
     (&
    0.39
    ണേ
    0.39
    వాన్ని
    0.39
    上也
    0.39
    Activations Density 0.002%

    No Known Activations