© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9832
    Prev
    Next
    INDEX
    Explanations

    dust and related things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ло
    1.54
    ן
    1.52
    نا
    1.41
    يه
    1.41
    st
    1.38
    te
    1.32
    millan
    1.28
    listed
    1.27
    ر
    1.27
    го
    1.27
    POSITIVE LOGITS
     Deportes
    1.61
    AY
    1.57
    ある
    1.51
     образом
    1.51
    ジネス
    1.48
     determinados
    1.45
     Monteiro
    1.45
     huesos
    1.45
     наличии
    1.44
     étudier
    1.44
    Activations Density 0.133%

    No Known Activations