© 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. 22-GEMMASCOPE-2-RES-16K
    7. 474
    Prev
    Next
    INDEX
    Explanations

    satisfaction and dissatisfaction

    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
     end
    0.63
      
    0.61
     once
    0.60
     most
    0.56
     so
    0.51
     (
    0.51
     piece
    0.51
     even
    0.49
     [
    0.49
     mid
    0.48
    POSITIVE LOGITS
    itative
    1.44
    ating
    1.43
    itation
    1.43
    iting
    1.40
    ative
    1.39
    iation
    1.38
    ition
    1.37
    iration
    1.33
    頩
    1.33
    <unused1460>
    1.32
    Activations Density 2.156%

    No Known Activations