© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1927
    Prev
    Next
    INDEX
    Explanations

    feeling insignificant or negative emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्ड
    1.05
    looking
    0.97
    Non
    0.92
    க்காக
    0.92
     по
    0.89
    мат
    0.84
    И
    0.83
    Previous
    0.83
    之間的
    0.83
    Considering
    0.83
    POSITIVE LOGITS
     significant
    1.05
    resx
    1.01
    〖
    0.98
    ර්ධ
    0.98
     privileged
    0.98
     bipolar
    0.97
    ngt
    0.96
     منٹو
    0.96
     kesulitan
    0.95
     motivation
    0.93
    Activations Density 0.127%

    No Known Activations