© 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. 28441
    Prev
    Next
    INDEX
    Explanations

    product reviews and recommendations

    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
     to
    -1.76
     into
    -1.29
     and
    -1.05
     для
    -0.98
    indd
    -0.90
     scalars
    -0.90
     onto
    -0.90
    cioc
    -0.89
     setDescription
    -0.89
    foreach
    -0.87
    POSITIVE LOGITS
    cartão
    1.09
    Garantía
    1.07
    Recomendaciones
    1.03
    Consejos
    1.02
    Opinión
    0.99
    Ventajas
    0.98
     PÅ
    0.96
    jelasan
    0.95
     dégust
    0.94
    Sonido
    0.90
    Activations Density 0.123%

    No Known Activations