© 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. 245575
    Prev
    Next
    INDEX
    Explanations

    articles/phrases

    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
     sepen
    0.50
     domains
    0.48
     phyll
    0.46
    "
    0.46
     —
    0.46
     conception
    0.45
     perfumes
    0.44
     ELF
    0.44
     Guilherme
    0.43
     monomers
    0.43
    POSITIVE LOGITS
    inetics
    0.52
    社会
    0.52
    <unused998>
    0.52
     አን
    0.51
     स्टार
    0.50
    slant
    0.49
     মিলিয়ন
    0.48
     बढ़ती
    0.48
     المرأة
    0.48
    ksjon
    0.47
    Activations Density 0.000%

    No Known Activations