© 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. 31-GEMMASCOPE-2-RES-262K
    7. 204847
    Prev
    Next
    INDEX
    Explanations

    would flow, speak in, before returning

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

    critiques insufficient

    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_31_width_262k_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
     टिक
    0.49
    াজিক
    0.48
    捲
    0.47
    ulk
    0.47
     ядра
    0.46
    唱歌
    0.46
     цін
    0.46
     berlang
    0.46
     কাদের
    0.46
    hauses
    0.45
    POSITIVE LOGITS
    0
    0.58
    E
    0.49
    ƒ
    0.44
    Delay
    0.43
     मृ
    0.42
    B
    0.41
    T
    0.40
    1
    0.40
    D
    0.40
    Either
    0.39
    Activations Density 0.003%

    No Known Activations