© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127999
    Prev
    Next
    INDEX
    Explanations

    intensified subjective 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
    美国的
    -1.52
     you
    -1.47
     delà
    -1.45
     EXERC
    -1.40
    余談
    -1.38
     getCity
    -1.34
     buhay
    -1.32
    >
    -1.30
    小镇
    -1.30
     iyon
    -1.30
    POSITIVE LOGITS
    或
    1.62
    atigable
    1.41
    силання
    1.41
    ных
    1.40
            
    1.39
    plotlib
    1.34
    ingual
    1.31
    や
    1.31
    只有
    1.31
     или
    1.31
    Activations Density 0.033%

    No Known Activations