© 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. 42250
    Prev
    Next
    INDEX
    Explanations

    erotic content

    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
    豋
    -2.52
    焢
    -2.39
    结语
    -2.36
    详解
    -2.23
    哔
    -2.16
     helg
    -2.13
     emot
    -2.13
     sista
    -2.09
    我们是
    -2.08
     歳
    -2.06
    POSITIVE LOGITS
    .
    3.53
     ที่
    2.33
     但
    2.27
     különböz
    2.25
     zwanzig
    2.16
    }
    2.13
     hossz
    2.05
     ,"
    2.00
     That
    1.97
    chown
    1.97
    Activations Density 0.004%

    No Known Activations