© 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. 35382
    Prev
    Next
    INDEX
    Explanations

    religious organizations and groups

    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
    </i>
    -1.27
    -1.26
     bedeckt
    -1.20
    arXiv
    -1.16
     also
    -1.12
    霾
    -1.07
     geraten
    -1.05
    2
    -1.05
     specification
    -1.04
     nominations
    -1.04
    POSITIVE LOGITS
    詆
    1.34
     suplementos
    1.27
    Hozzá
    1.24
     Irán
    1.24
     Tienen
    1.22
    Vlastnosti
    1.22
     fundador
    1.21
     vinaigre
    1.18
    Výhody
    1.16
    cipient
    1.16
    Activations Density 0.032%
    No Known Activations