© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84549
    Prev
    Next
    INDEX
    Explanations

    lives when

    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
    aerop
    -0.98
     when
    -0.92
    siębior
    -0.88
     samego
    -0.86
    businessman
    -0.85
    rrh
    -0.85
     in
    -0.82
     sosteniendo
    -0.81
     their
    -0.81
     follows
    -0.81
    POSITIVE LOGITS
    zyny
    0.95
    ߍ
    0.91
    ridis
    0.91
     ravages
    0.90
    tischer
    0.90
    volle
    0.89
     paintball
    0.87
    了口气
    0.86
    tivas
    0.85
    转换成
    0.84
    Activations Density 0.058%

    No Known Activations