© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236572
    Prev
    Next
    INDEX
    Explanations

    mineral oil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يبه
    0.42
     dinheiro
    0.42
    欲
    0.41
     beautiful
    0.40
     dinero
    0.39
    欲しい
    0.39
     Blum
    0.39
     couronne
    0.39
     Fournier
    0.39
     TextInputLayout
    0.39
    POSITIVE LOGITS
    aying
    0.54
    useks
    0.51
    ୦
    0.51
    apshot
    0.50
     आधार
    0.50
     গ্রীষ্ম
    0.50
    тур
    0.49
     পয়েন্ট
    0.49
     lätt
    0.49
    ภาพ
    0.48
    Activations Density 0.000%

    No Known Activations