© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8180
    Prev
    Next
    INDEX
    Explanations

    melhor, mejor

    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_22_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
     team
    0.98
    빌
    0.95
    team
    0.90
     Team
    0.87
    តាម
    0.87
    벨
    0.86
    πο
    0.85
    stl
    0.85
    ৩
    0.85
    মিস
    0.84
    POSITIVE LOGITS
    展開
    1.01
    يديا
    0.99
    odzi
    0.99
     сцена
    0.98
     cript
    0.98
    erà
    0.97
     {})
    0.97
    hnung
    0.96
     Notebook
    0.94
     примене
    0.94
    Activations Density 0.000%

    No Known Activations