© 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. 14761
    Prev
    Next
    INDEX
    Explanations

    measurements in inches and centimeters

    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
     indiscrimin
    1.07
     unsub
    1.07
    課
    1.05
     incurred
    1.04
     stockp
    1.03
     tota
    1.02
     multitudes
    1.00
     inú
    0.99
     multitude
    0.99
     voluminous
    0.97
    POSITIVE LOGITS
    ピン
    1.10
     मकान
    1.10
    번째
    1.09
    第二个
    1.08
    괵
    1.08
    第三
    1.07
    第二
    1.05
    第
    1.05
    Mentor
    1.05
     Парт
    1.03
    Activations Density 0.001%

    No Known Activations