© 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. 217711
    Prev
    Next
    INDEX
    Explanations

    Chapter closest

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

    cute undergraduate lovely

    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
     Guangzhou
    0.50
    вки
    0.48
    সি
    0.48
    ল
    0.48
    ক
    0.48
    广州
    0.48
     Blizzard
    0.47
    ล
    0.45
     Offshore
    0.45
    Shanghai
    0.44
    POSITIVE LOGITS
    antaranya
    0.47
     مشین
    0.43
     توانند
    0.42
     jedn
    0.42
     सीआर
    0.42
    moment
    0.42
     తన
    0.42
     ਹਨ
    0.42
     విద్య
    0.42
     hoeveel
    0.42
    Activations Density 0.000%

    No Known Activations