© 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. 22-GEMMASCOPE-RES-131K
    7. 129497
    Prev
    Next
    INDEX
    Explanations

    emotional states and conditions

    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
     eğer
    -1.09
    Athletics
    -1.06
    Grades
    -1.05
     Empieza
    -1.05
    ಿದೆ
    -1.05
    ondissement
    -1.04
     deflect
    -1.03
     smir
    -1.03
    lių
    -1.00
    ).
    -1.00
    POSITIVE LOGITS
    ness
    1.58
     you
    1.45
     they
    1.23
    现状
    1.21
    atser
    1.20
     липня
    1.19
     شدن
    1.16
     yourself
    1.16
     himo
    1.16
     person
    1.15
    Activations Density 0.053%

    No Known Activations