© 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. 86450
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    price comparisons and rankings

    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
    一
    0.27
    य
    0.27
     .
    0.26
    子
    0.26
     ,
    0.26
    way
    0.26
    action
    0.26
    9
    0.26
     -
    0.25
    ↵
    0.25
    POSITIVE LOGITS
     atualmente
    0.37
     extranj
    0.32
     femelles
    0.31
     saisons
    0.31
     مذکور
    0.31
     rendement
    0.31
     volledig
    0.30
     pertenec
    0.29
     korzyst
    0.29
     habitaciones
    0.29
    Activations Density 0.107%

    No Known Activations