© 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. 133357
    Prev
    Next
    INDEX
    Explanations

    C++ type declarations

    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
    黝
    0.42
     dicho
    0.41
     =>
    0.41
     deference
    0.38
    鏢
    0.37
     aver
    0.37
    大き
    0.37
     poorly
    0.37
     Vista
    0.37
     今回
    0.37
    POSITIVE LOGITS
     цветы
    0.43
     floods
    0.43
    財布
    0.41
    <bbox>
    0.40
    𝒎
    0.40
    म्म
    0.40
    हो
    0.40
     banjir
    0.39
    wallet
    0.39
    ୨
    0.39
    Activations Density 0.000%

    No Known Activations