© 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. 83060
    Prev
    Next
    INDEX
    Explanations

    Mach-related words and names

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

    The neuron activates on occurrences of the string “Mach” (e.g. in words like Mach, Mach‐Zehnder, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    リエステル
    -0.90
    věr
    -0.77
     самостоя
    -0.77
     Anſ
    -0.76
     Verf
    -0.75
    噁
    -0.75
     Guardia
    -0.73
    return
    -0.69
    \}$
    -0.68
     autentic
    -0.68
    POSITIVE LOGITS
     Mach
    1.41
    Mach
    1.19
     mach
    0.99
    mach
    0.96
     MACH
    0.92
     machined
    0.84
     Ze
    0.81
     viewing
    0.79
     machin
    0.79
    otar
    0.77
    Activations Density 0.012%

    No Known Activations