© 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. 48348
    Prev
    Next
    INDEX
    Explanations

    heart break

    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
    ANDRE
    -0.88
     tré
    -0.87
    HYDRO
    -0.82
    Nanos
    -0.80
    面白い
    -0.79
    ել
    -0.77
     poissons
    -0.75
     Confession
    -0.75
     bestand
    -0.75
     grotte
    -0.75
    POSITIVE LOGITS
     breaks
    3.45
     breaking
    2.98
     broke
    2.89
     break
    2.89
    breaks
    2.81
     Breaks
    2.78
    break
    2.53
    breaking
    2.45
     Breaking
    2.34
     Break
    2.31
    Activations Density 0.019%

    No Known Activations