© 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. 15598
    Prev
    Next
    INDEX
    Explanations

    exponents

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

    regular expressions and escaping

    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
     lemonade
    0.46
    治安
    0.43
    決済
    0.42
    鵑
    0.42
     matchmaking
    0.42
    วิน
    0.41
    接待
    0.41
    ჭ
    0.41
    უკ
    0.40
     entitlements
    0.40
    POSITIVE LOGITS
     Powers
    0.52
     Pow
    0.50
    powers
    0.50
     powers
    0.47
    Powers
    0.47
     Power
    0.45
    POWER
    0.45
     superscript
    0.44
     Powder
    0.44
    Pow
    0.42
    Activations Density 0.011%

    No Known Activations