© 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. 71420
    Prev
    Next
    INDEX
    Explanations

    Statistics of obl

    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
     or
    -1.49
     his
    -1.25
    </em>
    -1.16
     many
    -1.09
    </strong>
    -1.08
     and
    -0.97
     reform
    -0.97
     first
    -0.95
     more
    -0.93
     nine
    -0.93
    POSITIVE LOGITS
    specifically
    1.36
     ícones
    1.36
     particolarmente
    1.30
     mudou
    1.25
    particularly
    1.23
     querem
    1.23
    cisme
    1.22
    儇
    1.21
     camicia
    1.21
    𝒙
    1.20
    Activations Density 0.001%

    No Known Activations