© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71407
    Prev
    Next
    INDEX
    Explanations

    specific pairings following key terms

    np_acts-logits-general · gemini-2.5-flash-lite

    hexagram, talking, match, curious, foundation, six

    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
     combust
    0.49
     protons
    0.46
    Más
    0.43
    ᱱ
    0.42
     combustion
    0.42
     dwells
    0.41
     VERSION
    0.41
    instellung
    0.41
    λέ
    0.41
    н
    0.40
    POSITIVE LOGITS
    بین
    0.43
     türlü
    0.43
     نیم
    0.43
    เพราะ
    0.43
     ভবিষ্য
    0.42
    できるよう
    0.42
     هایی
    0.42
    वण्यासाठी
    0.42
     வழியாக
    0.42
     غیر
    0.41
    Activations Density 0.001%

    No Known Activations