© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7898
    Prev
    Next
    INDEX
    Explanations

    Job descriptions and roles

    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
    </h1>
    1.05
     tika
    1.02
    使い方
    1.02
    ５
    0.99
     siècles
    0.96
    으면
    0.95
    !')
    0.90
    它可以
    0.88
     века
    0.87
    ０
    0.87
    POSITIVE LOGITS
    Cn
    1.26
    Cannon
    1.20
    س
    1.17
    Camb
    1.17
    Surname
    1.16
    کنند
    1.16
     கிஷ
    1.15
    cn
    1.15
    ______________
    1.14
    स्वामी
    1.13
    Activations Density 0.012%

    No Known Activations