© 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. 34-GEMMASCOPE-RES-131K
    7. 103790
    Prev
    Next
    INDEX
    Explanations

    factor and factorisation

    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_34/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
    )：
    -1.15
    
    -1.13
     rattled
    -1.07
    nesium
    -1.05
    ophers
    -1.04
     escaleras
    -1.04
    神
    -1.03
    簠
    -1.03
    IDENTAL
    -1.02
    馀
    -1.02
    POSITIVE LOGITS
     Factor
    1.63
     you
    1.47
    Factor
    1.41
    factor
    1.35
     FACTOR
    1.23
    ar
    1.16
     factor
    1.13
    2
    1.08
    last
    1.07
    ized
    1.05
    Activations Density 0.039%

    No Known Activations