© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9016
    Prev
    Next
    INDEX
    Explanations

    webinvoke and metadata

    np_acts-logits-general · gemini-2.5-flash-lite

    code properties get set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    膛
    0.43
    VisualStyle
    0.42
    >);
    0.40
     وجود
    0.39
     persisted
    0.38
     अंतर्गत
    0.38
    不安定
    0.37
    ಮಾಣ
    0.37
    مرين
    0.37
    粦
    0.37
    POSITIVE LOGITS
    사를
    0.37
    wini
    0.37
    사가
    0.36
     నిర్మా
    0.36
     ಕೊಡ
    0.36
    Meta
    0.35
     Meta
    0.35
     Debe
    0.35
    ścia
    0.35
    ulpt
    0.35
    Activations Density 0.014%

    No Known Activations