© 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. 84518
    Prev
    Next
    INDEX
    Explanations

    compound nouns and phrases

    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
     копия
    -0.98
     אד
    -0.91
    LECTION
    -0.90
     frenos
    -0.88
     Tenemos
    -0.88
     mieten
    -0.88
     faisant
    -0.87
     Mejora
    -0.85
     Propiedad
    -0.85
     encendido
    -0.85
    POSITIVE LOGITS
     because
    1.16
     in
    1.05
     if
    1.02
     with
    0.98
     after
    0.90
     during
    0.88
     During
    0.83
    УДК
    0.82
    رائه
    0.82
     from
    0.81
    Activations Density 0.122%

    No Known Activations