© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87330
    Prev
    Next
    INDEX
    Explanations

    variable names with underscores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     For
    -1.74
     for
    -1.68
     Some
    -1.60
    onsumsi
    -1.59
    taines
    -1.59
    他
    -1.59
     misschien
    -1.53
    疼痛
    -1.53
    นี้
    -1.52
    ITAN
    -1.51
    POSITIVE LOGITS
     zwi
    2.08
     kollu
    1.94
    successfully
    1.79
     eighteen
    1.78
     nineteen
    1.77
     thirty
    1.77
     consegue
    1.77
    元々
    1.75
    種類の
    1.73
     "",
    1.73
    Activations Density 0.012%

    No Known Activations