© 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. 64680
    Prev
    Next
    INDEX
    Explanations

    positive emotions and cheerfulness

    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
     to
    -1.16
    In
    -1.16
     illetve
    -1.09
    in
    -1.09
     varying
    -1.04
    了出来
    -1.04
    E
    -1.02
     zupełnie
    -1.01
     словом
    -1.01
    異なる
    -0.99
    POSITIVE LOGITS
     positivity
    1.60
    positi
    1.50
     optimism
    1.44
    🩻
    1.39
    ポジ
    1.29
     оптими
    1.27
    HAPPY
    1.27
     HAPPY
    1.26
    Happiness
    1.26
    ectious
    1.25
    Activations Density 0.032%

    No Known Activations