© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    want or like

    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
     Til
    0.58
     Now
    0.52
    leading
    0.52
     together
    0.51
     Leading
    0.49
    ；
    0.49
    8
    0.49
     now
    0.48
    [-
    0.48
     Der
    0.48
    POSITIVE LOGITS
     want
    1.29
     wanting
    1.19
     хотите
    1.17
     desire
    1.15
     vuole
    1.14
     souhaitez
    1.09
     ingin
    1.09
     wants
    1.06
     desean
    1.05
     deseja
    1.03
    Activations Density 1.490%

    No Known Activations