© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    numbered lists or points

    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
    体制
    1.22
    ぷ
    1.01
    取代
    1.00
    プ
    1.00
    プラ
    0.99
    →
    0.97
     →
    0.96
    ）：
    0.96
     プ
    0.94
    出发
    0.92
    POSITIVE LOGITS
     nearly
    1.27
     bandits
    1.26
     almost
    1.25
     robberies
    1.25
     thieves
    1.21
     jaar
    1.21
     grandson
    1.20
     loneliness
    1.19
     robbery
    1.19
     grandkids
    1.19
    Activations Density 0.070%

    No Known Activations