© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 622
    Prev
    Next
    INDEX
    Explanations

    words and non-latin characters

    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_65k_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
    ისა
    0.71
     magari
    0.61
    훅
    0.61
    ymmet
    0.59
    semibold
    0.57
    proper
    0.54
    lessly
    0.54
     solidly
    0.54
    どうしても
    0.53
     genuinely
    0.52
    POSITIVE LOGITS
     خالد
    0.98
     Natalie
    0.96
     Benjamin
    0.94
     Manuel
    0.92
     Lien
    0.92
     हेनरी
    0.91
     ۔
    0.91
     Shelby
    0.91
     Portal
    0.91
     Bridget
    0.90
    Activations Density 0.160%

    No Known Activations