© 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. 31695
    Prev
    Next
    INDEX
    Explanations

    certain words followed by common words

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

    celebration, reliability, joy

    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
    者
    0.47
    iid
    0.45
    もん
    0.45
     сих
    0.44
    р
    0.44
    ل
    0.43
    ও
    0.43
    I
    0.43
    BoolVar
    0.42
    legi
    0.41
    POSITIVE LOGITS
     incluyendo
    0.51
     zbog
    0.49
     difficoltà
    0.44
     Xer
    0.44
     জড়িয়ে
    0.44
    ®,
    0.44
     جلوگیری
    0.43
    スの
    0.43
     éviter
    0.43
    الأ
    0.43
    Activations Density 0.000%

    No Known Activations