© 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. 5118
    Prev
    Next
    INDEX
    Explanations

    Questa Project

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

    Linux kernel

    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
    ل
    0.34
     daß
    0.27
     solcher
    0.27
     ResultSet
    0.26
     entfernen
    0.26
     samme
    0.25
    我国
    0.25
    zelfde
    0.25
     Verlet
    0.25
     indiquer
    0.25
    POSITIVE LOGITS
    은
    0.31
     למ
    0.27
     이야
    0.27
     자체
    0.26
    യുടെ
    0.26
     있는
    0.26
     કે
    0.26
     के
    0.25
    ეთის
    0.25
    ásra
    0.25
    Activations Density 0.691%

    No Known Activations