© 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. 12557
    Prev
    Next
    INDEX
    Explanations

    check in and out

    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
    y
    -1.95
     of
    -1.93
    t
    -1.90
    u
    -1.86
    st
    -1.84
    т
    -1.72
    x
    -1.70
    i
    -1.66
    en
    -1.63
    href
    -1.59
    POSITIVE LOGITS
    Упаковка
    1.83
    
    1.76
    Suka
    1.74
    Donativos
    1.66
     ralla
    1.65
     水墨
    1.60
    Mucha
    1.58
     comerci
    1.57
     friv
    1.57
     pases
    1.55
    Activations Density 0.007%

    No Known Activations