© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69297
    Prev
    Next
    INDEX
    Explanations

    date, journal, author, tag, branch, Nova Scotia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_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
     semiconductors
    1.60
     alike
    1.50
     again
    1.50
     opportunity
    1.50
     glasses
    1.47
    👆
    1.47
    ensity
    1.46
    🫶
    1.45
     tickets
    1.43
    otene
    1.39
    POSITIVE LOGITS
     засе
    1.07
     vivi
    1.04
     biên
    1.03
     реда
    1.03
     الد
    0.96
    tnie
    0.94
     jurnal
    0.94
    unile
    0.94
    ворю
    0.94
     chefe
    0.93
    Activations Density 0.000%

    No Known Activations