© 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. 10-GEMMASCOPE-RES-131K
    7. 1136
    Prev
    Next
    INDEX
    Explanations

    maintain ongoing existence/state

    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_10/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
    痦
    -2.66
    geſ
    -2.36
    鲞
    -2.34
    雱
    -2.30
    鼍
    -2.16
    勦
    -2.11
    旆
    -2.08
     Ciências
    -2.08
    tatu
    -2.06
    pompa
    -2.03
    POSITIVE LOGITS
    you
    2.45
    m
    2.41
    in
    2.34
    We
    2.27
    at
    2.22
    ch
    2.06
    ஂ
    2.06
                    
    2.05
    n
    2.02
    h
    2.02
    Activations Density 0.041%

    No Known Activations