© 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. 13512
    Prev
    Next
    INDEX
    Explanations

    strategies, #Invest, delegation, trust

    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
    𝗲
    1.15
    imm
    1.01
    beet
    0.99
    𝗸
    0.97
    rig
    0.96
    𝗹
    0.95
    𝗱
    0.95
    𝘀
    0.95
    𝗶
    0.92
     ог
    0.92
    POSITIVE LOGITS
     Nonlinear
    1.77
    APB
    1.65
     anúncios
    1.58
     perencanaan
    1.57
    acée
    1.57
     coisa
    1.55
     Accenture
    1.55
     Resilience
    1.54
     trabalhar
    1.53
     الإعلام
    1.53
    Activations Density 0.000%

    No Known Activations