© 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. 77371
    Prev
    Next
    INDEX
    Explanations

    constitution rules and requirements

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

    signed certificates

    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
     Medicines
    0.50
     ४
    0.46
    ické
    0.46
    rii
    0.45
     ਜਾਂ
    0.44
    riffe
    0.44
     Krankheit
    0.44
     ૩
    0.44
    ata
    0.44
     폭
    0.43
    POSITIVE LOGITS
    サル
    0.51
     lipoprotein
    0.49
     heartache
    0.46
    ITAL
    0.46
     gimnas
    0.45
     inexperienced
    0.45
     provved
    0.45
     adrenalin
    0.44
     gust
    0.43
     Lorenzo
    0.43
    Activations Density 0.001%

    No Known Activations