© 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. 70797
    Prev
    Next
    INDEX
    Explanations

    fads and trends

    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
    ).
    -1.80
    }$.
    -1.73
    <bos>
    -1.73
    ‌.
    -1.56
    JsonHelper
    -1.48
    IANGLES
    -1.46
    曩
    -1.46
    ."));
    -1.46
    ﹊
    -1.45
     vital
    -1.44
    POSITIVE LOGITS
     trends
    1.92
    </b>
    1.63
     passend
    1.43
     goud
    1.41
    vrouw
    1.39
    >
    1.39
    1
    1.38
     paling
    1.35
     it
    1.34
     problemet
    1.33
    Activations Density 0.026%

    No Known Activations