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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109846
    Prev
    Next
    INDEX
    Explanations

    words starting with mun

    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
     лиш
    -0.89
     exceeding
    -0.75
     iniciado
    -0.69
    ouan
    -0.69
     imply
    -0.69
     done
    -0.69
    ducted
    -0.69
    excuse
    -0.69
     similar
    -0.69
    together
    -0.69
    POSITIVE LOGITS
    Mun
    1.02
     Mun
    0.92
    ford
    0.84
    FORD
    0.81
     Bali
    0.79
     muni
    0.78
    tragung
    0.77
     COE
    0.77
     Deer
    0.76
     sommet
    0.75
    Activations Density 0.020%

    No Known Activations