© 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-16K
    7. 12792
    Prev
    Next
    INDEX
    Explanations

    it's okay to feel

    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_16k_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
     у
    0.87
     whenever
    0.86
    然后在
    0.84
     ст
    0.83
    Harm
    0.81
    за
    0.81
     would
    0.80
     हंस
    0.80
    ูด
    0.80
     कथ
    0.79
    POSITIVE LOGITS
     immature
    1.09
    ளுக்கான
    1.07
     capsid
    1.06
    Basic
    1.05
     検
    1.04
     spécifiques
    1.04
     Radioactive
    1.01
     mecánico
    1.00
    gé
    1.00
    ご飯
    1.00
    Activations Density 0.077%

    No Known Activations