© 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. 12131
    Prev
    Next
    INDEX
    Explanations

    fuse with parenthetical disambiguation

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

    URLs and hotlines

    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
     Why
    0.23
    ımızın
    0.22
    假设
    0.21
     yoga
    0.21
     Pilates
    0.21
     Warum
    0.21
    4
    0.21
    ４
    0.21
     Kubernetes
    0.20
     seamen
    0.20
    POSITIVE LOGITS
    ء
    0.22
    一番
    0.21
     вер
    0.21
     عبد
    0.20
     cliquer
    0.20
    ។
    0.19
    екст
    0.19
    .​​
    0.19
    த்தர
    0.19
    ं
    0.19
    Activations Density 0.110%

    No Known Activations