© 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. 22072
    Prev
    Next
    INDEX
    Explanations

    patents and publications

    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
    }],
    0.45
    recl
    0.43
     상담
    0.41
    铂
    0.41
    在美国
    0.40
    本発明
    0.40
    产业
    0.39
    赊
    0.39
    invention
    0.38
    鉑
    0.38
    POSITIVE LOGITS
    A
    0.46
     A
    0.45
    মুখে
    0.42
    Г
    0.41
    ａ
    0.41
     А
    0.40
    Ａ
    0.39
     reveals
    0.39
    сього
    0.38
     C
    0.38
    Activations Density 0.001%

    No Known Activations