© 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. 10-GEMMASCOPE-RES-131K
    7. 84728
    Prev
    Next
    INDEX
    Explanations

    psychedelic, psychosis, psychological, psyches

    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
    趼
    -3.02
    潆
    -3.00
    </sub>
    -2.92
    鰾
    -2.92
    )”
    -2.91
    跸
    -2.78
    钐
    -2.75
    踅
    -2.73
    </h3>
    -2.72
    聼
    -2.64
    POSITIVE LOGITS
    {
    3.17
    在
    2.69
    и
    2.59
    这里
    2.55
     \&
    2.48
    Если
    2.48
    家乡
    2.45
    Еще
    2.42
    Они
    2.38
    y
    2.33
    Activations Density 0.003%

    No Known Activations