© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128407
    Prev
    Next
    INDEX
    Explanations

    feelings of accomplishment and reward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -1.05
    明る
    -1.00
     литров
    -0.98
     invloed
    -0.95
     available
    -0.95
     ਵਿੱਚ
    -0.93
     parseFrom
    -0.91
    ってみました
    -0.91
     allora
    -0.90
     различных
    -0.90
    POSITIVE LOGITS
     when
    1.96
     satisfaction
    1.40
     gratification
    1.35
     accomplishment
    1.33
     ketika
    1.31
     عندما
    1.30
    when
    1.28
     after
    1.26
     success
    1.23
     gratified
    1.23
    Activations Density 0.026%

    No Known Activations