© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85705
    Prev
    Next
    INDEX
    Explanations

    emotional reactions and states

    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
     producen
    -2.08
     начали
    -2.02
    小型
    -1.98
    i
    -1.98
    ra
    -1.96
     It
    -1.89
     größten
    -1.88
    潜在
    -1.86
     ardent
    -1.84
     kesin
    -1.84
    POSITIVE LOGITS
     and
    2.88
    .
    2.47
    鬭
    2.27
    鷙
    2.20
    埽
    2.14
    😵
    2.13
    😪
    2.03
    镦
    2.02
     tramontina
    1.98
    蔸
    1.98
    Activations Density 0.024%

    No Known Activations