© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    youtube channel identifiers

    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
    ும்
    1.95
    .''
    1.77
    掬
    1.68
    .’’
    1.68
     Raised
    1.66
    ೫
    1.65
    ureen
    1.62
     pose
    1.60
    ksa
    1.60
    탬
    1.60
    POSITIVE LOGITS
    𝙧
    2.20
     rider
    2.18
    iž
    2.17
    ยนต์
    2.12
     handlebar
    2.08
    icletas
    2.06
     bicicleta
    2.05
     handlebars
    2.03
    𝙙
    2.02
    rider
    1.99
    Activations Density 0.673%

    No Known Activations