© 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. 45019
    Prev
    Next
    INDEX
    Explanations

    songs, plants

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

    castle, relatives, Minecraft, tokenizers

    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
     可愛
    0.54
     gegangen
    0.52
     applause
    0.49
    |,
    0.49
     SZ
    0.48
     ratio
    0.47
     acel
    0.47
    iscus
    0.47
     情報
    0.46
     gede
    0.46
    POSITIVE LOGITS
    腻
    0.52
     thường
    0.49
    入
    0.47
    想
    0.47
    告
    0.46
    踪
    0.46
    Migration
    0.46
    行
    0.45
    夜
    0.45
    婆
    0.45
    Activations Density 0.001%

    No Known Activations