© 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. 35097
    Prev
    Next
    INDEX
    Explanations

    applying to you

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

    spatial memory

    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
    单词
    0.47
     officially
    0.46
     Financial
    0.45
    字段
    0.45
     Inter
    0.43
     ,
    0.43
     发表
    0.43
     nuove
    0.43
    /*
    0.42
    已经
    0.42
    POSITIVE LOGITS
     permettre
    0.63
     permettant
    0.62
    Beim
    0.54
     permettent
    0.51
     nutritive
    0.51
     motility
    0.50
     venen
    0.48
    Während
    0.48
     macer
    0.47
     mutagenesis
    0.47
    Activations Density 0.000%

    No Known Activations