© 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. 248746
    Prev
    Next
    INDEX
    Explanations

    conversion, summary, university, shopping, MERS

    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
     広
    0.49
    istique
    0.47
     Règ
    0.47
     кушымта
    0.47
     спасибо
    0.47
     இந்ந
    0.46
     акчага
    0.46
    юсь
    0.46
     సిని
    0.45
     җиңү
    0.45
    POSITIVE LOGITS
    Ab
    0.46
    ，
    0.45
    Activities
    0.44
    Entry
    0.44
    ด
    0.44
    Decrease
    0.44
    Enjoy
    0.43
    第
    0.43
    Favor
    0.42
    date
    0.42
    Activations Density 0.000%

    No Known Activations