© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104475
    Prev
    Next
    INDEX
    Explanations

    Mulan kill; tell her; visions only

    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
     you
    -1.80
    itaji
    -1.47
    före
    -1.45
    JPG
    -1.39
     I
    -1.39
     иногда
    -1.38
    躋
    -1.36
    踔
    -1.34
    当即
    -1.33
    !
    -1.30
    POSITIVE LOGITS
     bewusst
    1.76
     aufgrund
    1.38
     dovr
    1.36
     景色
    1.36
     by
    1.36
     menggunakan
    1.32
     afla
    1.32
     weiterhin
    1.30
    endet
    1.29
    很久
    1.29
    Activations Density 0.041%

    No Known Activations