© 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. 34-GEMMASCOPE-RES-131K
    7. 92693
    Prev
    Next
    INDEX
    Explanations

    romantic romantic side actors giving public anal

    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_34/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
     теку
    -1.01
    大き
    -0.98
    我先
    -0.95
     Instagram
    -0.91
     ✨
    -0.91
    ین
    -0.90
     послед
    -0.90
    称为
    -0.89
    <strong>
    -0.89
     Từ
    -0.89
    POSITIVE LOGITS
     doze
    1.07
    utuhkan
    1.00
     ـ
    1.00
     hereby
    0.98
    CHEMISTRY
    0.93
    När
    0.92
     whatsoever
    0.92
    اتور
    0.91
     Calcul
    0.91
     booklet
    0.91
    Activations Density 0.040%

    No Known Activations