© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40256
    Prev
    Next
    INDEX
    Explanations

    Academic and technical 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
     balcón
    -1.26
     jueces
    -1.10
     censored
    -1.09
     dormitorios
    -1.03
    unpublished
    -1.01
    sneakers
    -0.98
    Przy
    -0.98
     autobús
    -0.94
    '&:
    -0.94
     katika
    -0.93
    POSITIVE LOGITS
    bemos
    1.13
    jecture
    1.07
     evitare
    1.05
     you
    1.04
    BIBLIO
    1.03
     occasional
    0.99
    cre
    0.99
    arroll
    0.98
     we
    0.97
     will
    0.95
    Activations Density 0.004%

    No Known Activations