© 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. 117875
    Prev
    Next
    INDEX
    Explanations

    get a win or advantage

    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
    房間
    -0.86
    cová
    -0.84
    乁
    -0.83
    íté
    -0.81
     infek
    -0.81
     красота
    -0.80
     "/
    -0.79
    formen
    -0.79
     allora
    -0.78
    ꧀
    -0.77
    POSITIVE LOGITS
     extend
    1.49
     extending
    1.38
     maintain
    1.38
     move
    1.30
     keeps
    1.29
     maintains
    1.23
     puts
    1.23
     continue
    1.23
     keep
    1.23
     put
    1.20
    Activations Density 0.024%

    No Known Activations