© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16227
    Prev
    Next
    INDEX
    Explanations

    Michael Birch

    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
     упаковки
    -1.12
    Accordingly
    -1.04
     groet
    -1.02
    Consequently
    -0.96
     ešte
    -0.94
    させていただきます
    -0.93
    haup
    -0.92
    isies
    -0.91
     ușor
    -0.90
    cartes
    -0.90
    POSITIVE LOGITS
     entera
    1.00
    ׇ
    0.96
     Bar
    0.95
    strtotime
    0.88
    渲染
    0.85
     conced
    0.85
     half
    0.85
     anything
    0.85
     around
    0.85
     rodea
    0.85
    Activations Density 0.004%

    No Known Activations