© 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. 10-GEMMASCOPE-RES-131K
    7. 21756
    Prev
    Next
    INDEX
    Explanations

    cistern, restaur, endian, inexcusable, redistribution

    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_10/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
    “
    -3.30
     ſever
    -2.47
    夲
    -2.27
     笔画
    -2.25
     asisten
    -2.20
    ляции
    -2.19
     praktischen
    -2.17
    ’
    -2.16
     但是
    -2.11
     kompres
    -2.11
    POSITIVE LOGITS
    ]
    2.91
     renewed
    2.22
    {
    2.19
     parlak
    2.11
    欵
    2.09
    end
    2.06
     instill
    2.05
    }
    2.02
     innov
    2.02
     n
    2.02
    Activations Density 0.009%

    No Known Activations