© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19077
    Prev
    Next
    INDEX
    Explanations

    expression of satisfaction

    np_acts-logits-general · gemini-2.5-flash-lite

    satisfaction and happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    К
    0.71
    କ
    0.62
    ન
    0.58
    如果有
    0.57
    ส
    0.56
    要注意
    0.55
    čili
    0.55
    여러
    0.55
    ش
    0.55
    害怕
    0.54
    POSITIVE LOGITS
     Satisfaction
    1.31
     satisfied
    1.30
     Satisf
    1.25
     satisfaction
    1.24
    満足
    1.17
    satisf
    1.14
     만족
    1.14
     zufrieden
    1.11
     satisfying
    1.10
     satisf
    1.09
    Activations Density 0.065%

    No Known Activations