© 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. 10-GEMMASCOPE-RES-131K
    7. 15006
    Prev
    Next
    INDEX
    Explanations

    emotional responses

    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_10/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
    しなかった
    -1.52
    Sedangkan
    -1.50
    Mereka
    -1.48
    していますが
    -1.48
    Selanjutnya
    -1.47
    Namun
    -1.45
    Tetapi
    -1.44
    ︲
    -1.41
    Sementara
    -1.41
    Kepala
    -1.37
    POSITIVE LOGITS
    😨
    1.63
    😖
    1.55
    😤
    1.49
     etui
    1.48
    😠
    1.46
    😑
    1.45
    😳
    1.44
    🥺
    1.41
     quat
    1.41
     ★★★
    1.39
    Activations Density 0.036%

    No Known Activations