© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    being upset

    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
    N
    -2.53
    Is
    -2.45
    K
    -2.36
     y
    -2.34
     to
    -2.33
    C
    -2.28
     It
    -2.27
    It
    -2.23
    鏷
    -2.19
    T
    -2.16
    POSITIVE LOGITS
     soñ
    2.20
    penuhi
    2.17
    尨
    2.13
    enced
    2.06
    NOSIS
    2.02
     ſta
    2.00
    ка
    1.98
    妧
    1.98
    虓
    1.97
     Also
    1.93
    Activations Density 0.002%

    No Known Activations