© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4715
    Prev
    Next
    INDEX
    Explanations

    quality of understanding

    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_22_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
    Activities
    0.71
    ீரி
    0.65
    Activity
    0.64
     Activity
    0.63
     activity
    0.63
     aktivitas
    0.63
     деятельность
    0.62
    김
    0.60
     કરોડ
    0.59
     結果
    0.59
    POSITIVE LOGITS
     understanding
    1.67
    understanding
    1.47
     compréhension
    1.43
     Understanding
    1.41
    Understanding
    1.38
     Verständnis
    1.36
     understandings
    1.35
     comprensión
    1.28
     compreensão
    1.25
    理解
    1.23
    Activations Density 0.405%

    No Known Activations