© 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. 113278
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
    鱻
    -2.64
    ୈ
    -2.63
    昞
    -2.61
    曁
    -2.45
    澁
    -2.39
    ቭ
    -2.39
    偌
    -2.36
    無料で
    -2.34
     dueños
    -2.34
    鰱
    -2.33
    POSITIVE LOGITS
    '
    3.28
    </b>
    2.72
    .
    2.63
    -
    2.25
    </h5>
    2.22
     besonder
    2.19
    меты
    2.14
    𐬹
    2.08
     verlang
    2.08
     решила
    2.05
    Activations Density 0.006%

    No Known Activations