© 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. 13471
    Prev
    Next
    INDEX
    Explanations

    reading individual characters

    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
     odc
    -1.12
    taler
    -1.09
    关于
    -1.09
    zów
    -1.02
     fifth
    -1.02
    now
    -1.02
    onnaise
    -1.02
    ′-
    -1.01
     you
    -1.00
    BAND
    -1.00
    POSITIVE LOGITS
     character
    1.20
     letters
    1.04
    actrice
    1.03
     letter
    1.01
    olata
    1.01
    weeted
    0.98
    Soporte
    0.97
     averiguar
    0.97
     añadido
    0.97
    Nightmare
    0.97
    Activations Density 0.028%

    No Known Activations