© 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. 51155
    Prev
    Next
    INDEX
    Explanations

    code snippets with colons

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

    technical or scientific terms

    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
     /*
    0.54
    ंग
    0.54
    .//
    0.49
    ArrayList
    0.47
    /*
    0.46
     Notifications
    0.45
    ArchivePath
    0.45
     \}$
    0.44
    .\\
    0.44
    łąd
    0.44
    POSITIVE LOGITS
     cortical
    0.59
     queryset
    0.55
    é
    0.54
     phyt
    0.54
     rectal
    0.53
     steril
    0.52
    pygame
    0.52
     follicle
    0.52
     sarcom
    0.52
    ᆭ
    0.51
    Activations Density 0.000%

    No Known Activations