© 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. 225885
    Prev
    Next
    INDEX
    Explanations

    localizing texts and services

    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
     CRUIS
    0.51
    
    0.50
     dentées
    0.46
     oblivion
    0.46
     dvi
    0.46
     쌍
    0.45
     fui
    0.45
     televiz
    0.45
     میلیارد
    0.45
    Ꮫ
    0.45
    POSITIVE LOGITS
    ificar
    0.52
    gados
    0.51
    েনা
    0.48
    adá
    0.46
    更大
    0.46
    更高
    0.46
    anças
    0.45
    epers
    0.45
    enje
    0.45
    apos
    0.44
    Activations Density 0.000%

    No Known Activations