© 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. 102719
    Prev
    Next
    INDEX
    Explanations

    version information or package dependencies

    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
     conventions
    -0.76
    Cecil
    -0.72
     youngest
    -0.71
     schönsten
    -0.70
     heaven
    -0.66
     christlichen
    -0.66
    LoginActivity
    -0.63
    Jav
    -0.62
    Spes
    -0.62
     third
    -0.62
    POSITIVE LOGITS
     Persistent
    0.75
     εκεί
    0.74
    alla
    0.73
    UrlEncoded
    0.73
    safe
    0.69
     jaz
    0.69
    Guru
    0.69
    Persistent
    0.69
    RESH
    0.68
     Bum
    0.68
    Activations Density 0.091%

    No Known Activations