© 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. 105422
    Prev
    Next
    INDEX
    Explanations

    idiot, moron, addict descriptors

    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
    豨
    -2.39
     acoged
    -2.34
    e
    -2.28
    。）
    -2.23
    。“
    -2.22
    I
    -2.16
    𐀀
    -2.16
    。
    -2.16
     Conſ
    -2.14
    剮
    -2.14
    POSITIVE LOGITS
    }
    4.13
    .
    3.78
    {
    3.48
     This
    2.28
    ność
    2.19
     работой
    2.16
     What
    2.14
    锷
    2.14
    可以
    2.08
     fulfilment
    2.05
    Activations Density 0.004%

    No Known Activations