© 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. 30808
    Prev
    Next
    INDEX
    Explanations

    new words and images

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

    new and unusual

    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
    ために
    0.45
     টেব
    0.44
    TARGETTING
    0.41
     パ
    0.41
    パラメータ
    0.40
    昆
    0.40
    のために
    0.40
    待ち
    0.39
    撫
    0.39
    طن
    0.39
    POSITIVE LOGITS
     न्यू
    0.56
     Yeni
    0.56
     New
    0.52
     nových
    0.52
     neuen
    0.51
    न्यू
    0.48
     Ново
    0.47
     új
    0.47
     setNew
    0.47
     Neuen
    0.47
    Activations Density 0.033%

    No Known Activations