© 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. 222007
    Prev
    Next
    INDEX
    Explanations

    code definition snippets

    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
    ୨
    0.37
    凊
    0.36
    unächst
    0.36
     gacch
    0.36
    \{{}\
    0.35
    বরা
    0.35
    黢
    0.35
    number
    0.35
    raction
    0.35
    ուն
    0.34
    POSITIVE LOGITS
     сильнее
    0.40
     integrator
    0.40
     Writer
    0.39
    =('
    0.39
     Moore
    0.39
     모델
    0.38
     تدخل
    0.38
    ادل
    0.38
     Co
    0.38
     transpose
    0.38
    Activations Density 0.000%

    No Known Activations