© 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. 175088
    Prev
    Next
    INDEX
    Explanations

    words associated with rulers and strategy

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

    large models and information

    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
     descoberta
    0.43
    ب
    0.41
     bier
    0.41
     Mae
    0.40
     สมการ
    0.39
     Chr
    0.39
    Repr
    0.39
     ja
    0.39
     passport
    0.38
     papier
    0.38
    POSITIVE LOGITS
    URNIZOR
    0.54
    APPROVAL
    0.50
    ﻞ
    0.50
    forced
    0.50
    aloo
    0.50
    \},\{
    0.49
    ﺸ
    0.49
    }}^{-
    0.48
    getCql
    0.48
    ECUTIVE
    0.47
    Activations Density 0.000%

    No Known Activations