© 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. 148479
    Prev
    Next
    INDEX
    Explanations

    referring to previously mentioned items

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

    referring to above instructions or data

    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
     Noether
    0.54
    :\\
    0.52
     allons
    0.52
     Allgemeine
    0.52
     moſt
    0.52
     Protecting
    0.52
     Dewan
    0.51
     Toda
    0.51
     Thé
    0.50
    <unused347>
    0.50
    POSITIVE LOGITS
    mentioned
    0.68
     مذکور
    0.61
    提到的
    0.61
     mentioned
    0.60
    上述
    0.60
    j
    0.56
     aforementioned
    0.55
    foresaid
    0.55
    上記
    0.55
    ва
    0.54
    Activations Density 0.038%

    No Known Activations