© 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. 202353
    Prev
    Next
    INDEX
    Explanations

    map showing or mapping out

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

    map and mapping

    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
    ᆫ
    0.71
    مش
    0.69
     крас
    0.67
    ut
    0.66
     طور
    0.64
    咿
    0.64
     مجموع
    0.64
    unghi
    0.64
     incó
    0.63
    éth
    0.62
    POSITIVE LOGITS
    ו
    0.98
     Mapping
    0.93
     maps
    0.86
     Maps
    0.86
     mapping
    0.85
     Map
    0.82
    mapper
    0.81
     mappings
    0.79
    map
    0.77
     map
    0.76
    Activations Density 0.028%

    No Known Activations