© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11330
    Prev
    Next
    INDEX
    Explanations

    technical facts or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     向
    1.02
    进程
    0.95
     或
    0.92
     স্টার
    0.90
    ュ
    0.90
     आएगी
    0.84
    ຖ
    0.83
    発展
    0.83
     veya
    0.83
    슷
    0.82
    POSITIVE LOGITS
     chloroform
    1.05
     bathrobe
    1.03
     Hendricks
    1.02
    contentInset
    1.01
     ministries
    1.01
     oficinas
    1.00
     зробити
    1.00
     dermatology
    1.00
     dentistry
    0.98
     Министерство
    0.98
    Activations Density 0.000%

    No Known Activations