© 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. 70426
    Prev
    Next
    INDEX
    Explanations

    open

    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
    ],
    -1.16
     know
    -1.08
     zowel
    -1.02
     as
    -0.94
    巂
    -0.94
     encuent
    -0.93
     cobr
    -0.92
    ⃨
    -0.91
    鋤
    -0.90
    ities
    -0.89
    POSITIVE LOGITS
    女優
    0.98
    with
    0.96
    是指
    0.96
    俳優
    0.95
    quelize
    0.92
     baumwolle
    0.91
    ventajas
    0.91
    or
    0.90
     Behör
    0.90
     tekno
    0.89
    Activations Density 0.081%

    No Known Activations