© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75646
    Prev
    Next
    INDEX
    Explanations

    cities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.33
     typically
    -1.32
    凄く
    -1.26
    ことから
    -1.26
     along
    -1.24
    Typically
    -1.23
    ほんとに
    -1.17
     Typically
    -1.11
     that
    -1.10
     prestazioni
    -1.09
    POSITIVE LOGITS
    ⌥
    1.20
    地看着
    1.11
     مخصوص
    1.11
    
    1.11
     الحكومة
    1.09
     cuivre
    1.09
    𝟭
    1.08
    ♯
    1.06
    Ṡ
    1.05
     lecker
    1.04
    Activations Density 0.045%

    No Known Activations