© 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. 237317
    Prev
    Next
    INDEX
    Explanations

    digital or institutional contexts

    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
    再说
    0.45
    而出
    0.43
    ৃত্য
    0.42
    可以通过
    0.42
    Bing
    0.42
    通過
    0.41
    可以看到
    0.41
    隋
    0.41
    是通过
    0.41
    $("#
    0.40
    POSITIVE LOGITS
     khoản
    0.52
     th
    0.50
     inbox
    0.50
     yard
    0.49
     último
    0.49
    _
    0.49
     acre
    0.48
     nekoliko
    0.48
    voy
    0.48
     entirety
    0.47
    Activations Density 0.001%

    No Known Activations