© 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. 131825
    Prev
    Next
    INDEX
    Explanations

    computational concepts scaled

    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
     sio
    0.41
    ামত
    0.41
    сий
    0.38
    略
    0.37
    យ៉ាង
    0.37
     चाहे
    0.37
    稍微
    0.37
    вающей
    0.37
     वर्षीय
    0.36
     Slightly
    0.36
    POSITIVE LOGITS
     (>
    0.89
     (<
    0.61
     $(<
    0.54
     जिन्हें
    0.54
    和大
    0.48
    (<
    0.47
     virkelig
    0.46
    க்கொண்ட
    0.45
    すぎて
    0.42
     overwhel
    0.42
    Activations Density 0.060%

    No Known Activations